Skip to content

Commit ee3817c

Browse files
jacob-patternjacob-pattern
authored
Merge pull request #5 from patterninc/chore/interface-aidlc-cleanup
Align Code Mint with interface outcomes
2 parents 3ba5443 + f6b48a0 commit ee3817c

32 files changed

Lines changed: 303 additions & 170 deletions

File tree

‎.agents/code-mint-status.json‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,9 @@
11
{
2-
"code_mint": "1.0",
2+
"code_mint": "1.1",
33
"scope": ".",
44
"onboarded_at": null,
55
"last_validated": null,
6+
"heritage": null,
67
"outcomes": {
78
"validate_current_state": { "status": "Not Started", "date": null },
89
"navigate": { "status": "Not Started", "date": null },

.agents/skills/autonomy--env-auditor/SKILL.md renamed to .agents/skills/autonomy-env-auditor/SKILL.md

Lines changed: 22 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,21 @@
11
---
2-
name: autonomy--env-auditor
3-
description: Audit whether a repository's environment variable configuration allows an agent to load all required .env variables from scratch. Use when evaluating a new repository's agent-readiness, when environment loading fails during agent setup, or as part of an initial harness assessment. Do not use when .env files already load correctly and the goal is to add a single new variable, or when creating env loading capability (use autonomy--env-creator).
2+
name: autonomy-env-auditor
3+
description: Audit whether a repository's environment variable configuration allows an agent to load all required .env variables from scratch. Use when evaluating a new repository's agent-readiness, when environment loading fails during agent setup, or as part of an initial harness assessment. Do not use when .env files already load correctly and the goal is to add a single new variable, or when creating env loading capability (use autonomy-env-creator).
44
---
55

66
# Environment Auditor
77

88
Evaluate whether an agent can configure and load all required environment variables from a cold start — with zero pre-existing `.env` files or manual setup.
99

10+
## Discipline
11+
12+
This auditor follows code-mint's shared auditor discipline:
13+
14+
- **Depth option** — default `standard`; use `quick` for a sanity check on a recently audited repo or `deep` for legacy codebases, quarterly refreshes, or high-risk readiness claims. Heritage classification from `meta-onboarding` Phase 0 sets a sensible default.
15+
- **Calibration** — every report ends with a Calibration section naming the depth used, confidence level, what was not checked, and what would raise confidence. This is a required artifact, not a disclaimer.
16+
17+
This discipline is inspired by AWS AI-DLC's adaptive-depth and overconfidence-prevention ideas, but code-mint does not vendor or implement the full AI-DLC workflow.
18+
1019
## Step 1: Discover Environment Requirements
1120

1221
1. **Find all environment variable references** in the codebase:
@@ -60,7 +69,7 @@ Ensure the report directory exists: `mkdir -p .agents/reports/completed && touch
6069

6170
Ensure `.gitignore` ignores generated report contents while preserving the directories with their `.gitkeep` files.
6271

63-
Write the report to `.agents/reports/autonomy--env-auditor-audit.md`:
72+
Write the report to `.agents/reports/autonomy-env-auditor-audit.md`:
6473

6574
```
6675
# Environment Audit Report
@@ -87,13 +96,21 @@ Write the report to `.agents/reports/autonomy--env-auditor-audit.md`:
8796
- **Current State:** [what exists]
8897
- **Required State:** [what should exist]
8998
- **Recommended Action:** [specific step]
90-
- **Next Skill / Step:** [e.g., Run `autonomy--env-creator`]
99+
- **Next Skill / Step:** [e.g., Run `autonomy-env-creator`]
91100
92101
## Cold Start Blockers
93102
[List of variables that prevent application startup]
94103
95104
## Next Steps
96-
Run `autonomy--env-creator` to remediate findings.
105+
Run `autonomy-env-creator` to remediate findings.
106+
107+
## Calibration
108+
**Depth:** [quick / standard / deep]
109+
**Confidence:** [High / Medium / Low] — [one-sentence reason]
110+
**Not checked:**
111+
- [specific area + reason]
112+
**To raise confidence:**
113+
- [specific next step]
97114
```
98115

99116
After writing the report, update `docs/onboarding-checklist.md` and `.agents/code-mint-status.json` with the current `smoke_path` outcome status and date. Optionally update `docs/skills-status.md` if the repository keeps the compatibility view.

.agents/skills/autonomy--env-creator/SKILL.md renamed to .agents/skills/autonomy-env-creator/SKILL.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,17 +1,17 @@
11
---
2-
name: autonomy--env-creator
3-
description: Creates the capacity for an agent to load all environment variables from scratch, based on the output of autonomy--env-auditor. Use when an env audit report exists and environment loading needs to be remediated. Do not use when no audit report exists (run autonomy--env-auditor first) or when debugging a single missing variable.
2+
name: autonomy-env-creator
3+
description: Creates the capacity for an agent to load all environment variables from scratch, based on the output of autonomy-env-auditor. Use when an env audit report exists and environment loading needs to be remediated. Do not use when no audit report exists (run autonomy-env-auditor first) or when debugging a single missing variable.
44
---
55

66
# Environment Creator
77

8-
Build out a repository's environment variable configuration so that an agent (or new developer) can go from zero to a fully configured `.env` in a single command. Based on findings from `autonomy--env-auditor`.
8+
Build out a repository's environment variable configuration so that an agent (or new developer) can go from zero to a fully configured `.env` in a single command. Based on findings from `autonomy-env-auditor`.
99

1010
Prefer one documented bootstrap path that writes local env config from the repo's real source of truth. In many repos that is `scripts/env.sh`. A `.env.example` file can still exist, but it should be secondary.
1111

1212
## Prerequisites
1313

14-
Read the audit report at `.agents/reports/autonomy--env-auditor-audit.md`. If no report exists, instruct the user to run `autonomy--env-auditor` first.
14+
Read the audit report at `.agents/reports/autonomy-env-auditor-audit.md`. If no report exists, instruct the user to run `autonomy-env-auditor` first.
1515

1616
Before changing anything:
1717

@@ -242,5 +242,5 @@ Update the project's AGENTS.md and/or README to include:
242242
3. Start the application and verify it boots successfully.
243243
4. If generation or startup verification fails, keep the old `.env` in place or restore it from the backup before trying again.
244244
5. If a `.env.example` file exists, keep it as a reference or compatibility file only. Point it to the primary bootstrap path if helpful.
245-
6. Archive the audit report to `.agents/reports/completed/autonomy--env-auditor-audit-{YYYY-MM-DD}.md`.
245+
6. Archive the audit report to `.agents/reports/completed/autonomy-env-auditor-audit-{YYYY-MM-DD}.md`.
246246
7. Update `docs/onboarding-checklist.md` and `.agents/code-mint-status.json` with the current `smoke_path` outcome status and date. Optionally update `docs/skills-status.md` if the repository keeps the compatibility view.

.agents/skills/autonomy--sre-auditor/SKILL.md renamed to .agents/skills/autonomy-sre-auditor/SKILL.md

Lines changed: 23 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
---
2-
name: autonomy--sre-auditor
3-
description: Audit whether an agent has working access to the SRE CLIs the project uses — version control host CLI, cloud provider CLI, and observability CLI. Tests each connection and reports access gaps. The steps below use GitHub CLI, AWS CLI, and Datadog Pup as a worked example; adapt for your project's actual tooling. Use when setting up a new agent environment, troubleshooting tool access, or as part of an initial harness assessment. Do not use when debugging a specific production issue (use autonomy--sre-agent) or when auditing general runtime readiness (use autonomy--runtime-auditor).
2+
name: autonomy-sre-auditor
3+
description: Audit whether an agent has working access to the SRE CLIs the project uses — version control host CLI, cloud provider CLI, and observability CLI. Tests each connection and reports access gaps. The steps below use GitHub CLI, AWS CLI, and Datadog Pup as a worked example; adapt for your project's actual tooling. Use when setting up a new agent environment, troubleshooting tool access, or as part of an initial harness assessment. Do not use when debugging a specific production issue (use interface-sre-agent) or when auditing general runtime readiness (use autonomy-staging-auditor).
44
---
55

66
# SRE Auditor
@@ -9,6 +9,15 @@ Verify that an agent has authenticated, working access to the CLI tools required
99

1010
The steps below use **GitHub CLI, AWS CLI, and Datadog Pup** as a reference profile. If your project uses a different VCS host (e.g., GitLab, Azure DevOps), cloud provider (e.g., GCP, Azure), or observability platform (e.g., Grafana, New Relic, Prometheus), substitute the equivalent CLI and read-only verification commands while following the same audit structure.
1111

12+
## Discipline
13+
14+
This auditor follows code-mint's shared auditor discipline:
15+
16+
- **Depth option** — default `standard`; use `quick` for a sanity check on a recently audited repo or `deep` for legacy codebases, quarterly refreshes, or high-risk readiness claims. Heritage classification from `meta-onboarding` Phase 0 sets a sensible default.
17+
- **Calibration** — every report ends with a Calibration section naming the depth used, confidence level, what was not checked, and what would raise confidence. This is a required artifact, not a disclaimer.
18+
19+
This discipline is inspired by AWS AI-DLC's adaptive-depth and overconfidence-prevention ideas, but code-mint does not vendor or implement the full AI-DLC workflow.
20+
1221
## Step 1: Audit GitHub CLI Access
1322

1423
### Check Installation
@@ -107,15 +116,15 @@ For each monitoring tool, verify that output is machine-readable:
107116
- [ ] Traces connect requests across services
108117
- [ ] Error context includes stack traces, request IDs, and relevant input data
109118

110-
Machine-readable telemetry is required for `autonomy--sre-agent` to operate effectively.
119+
Machine-readable telemetry is required for `interface-sre-agent` to operate effectively.
111120

112121
## Output
113122

114123
Ensure the report directory exists: `mkdir -p .agents/reports/completed && touch .agents/reports/.gitkeep .agents/reports/completed/.gitkeep`
115124

116125
Ensure `.gitignore` ignores generated report contents while preserving the directories with their `.gitkeep` files.
117126

118-
Write the report to `.agents/reports/autonomy--sre-auditor-audit.md`:
127+
Write the report to `.agents/reports/autonomy-sre-auditor-audit.md`:
119128

120129
```
121130
# SRE Tooling Audit Report
@@ -166,10 +175,18 @@ Write the report to `.agents/reports/autonomy--sre-auditor-audit.md`:
166175
- **Current State:** [what exists]
167176
- **Required State:** [what should exist]
168177
- **Recommended Action:** [specific step]
169-
- **Next Skill / Step:** [e.g., Install/authenticate tooling manually, then re-run `autonomy--sre-auditor`; once ready, use `autonomy--sre-agent`]
178+
- **Next Skill / Step:** [e.g., Install/authenticate tooling manually, then re-run `autonomy-sre-auditor`; once ready, use `interface-sre-agent`]
170179
171180
## Next Steps
172-
Address findings to enable `autonomy--sre-agent` to operate effectively. If tooling or auth is missing, complete the manual install/authentication work first, then re-run `autonomy--sre-auditor`.
181+
Address findings to enable `interface-sre-agent` to operate effectively. If tooling or auth is missing, complete the manual install/authentication work first, then re-run `autonomy-sre-auditor`.
182+
183+
## Calibration
184+
**Depth:** [quick / standard / deep]
185+
**Confidence:** [High / Medium / Low] — [one-sentence reason]
186+
**Not checked:**
187+
- [specific area + reason]
188+
**To raise confidence:**
189+
- [specific next step]
173190
```
174191

175192
After writing the report, update `docs/onboarding-checklist.md` and `.agents/code-mint-status.json` with the current `sre_investigation` outcome status and date. Optionally update `docs/skills-status.md` if the repository keeps the compatibility view.

.agents/skills/autonomy--runtime-auditor/SKILL.md renamed to .agents/skills/autonomy-staging-auditor/SKILL.md

Lines changed: 23 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,21 @@
11
---
2-
name: autonomy--runtime-auditor
3-
description: Audit whether an AI agent can go from a clean checkout to a runnable application or local runtime equivalent, without unsafe provisioning or destructive setup. Use when evaluating development or staging-like runtime readiness, onboarding a new project, or checking whether the agent can install dependencies, start services, and perform smoke checks. Do not use when evaluating test strategy and coverage depth (use autonomy--test-readiness-auditor) or when debugging a live production issue (use autonomy--sre-agent).
2+
name: autonomy-staging-auditor
3+
description: Audit whether an AI agent can go from a clean checkout to a runnable application or local runtime equivalent, without unsafe provisioning or destructive setup. Use when evaluating development or staging-like runtime readiness, onboarding a new project, or checking whether the agent can install dependencies, start services, and perform smoke checks. Do not use when evaluating test strategy and coverage depth (use autonomy-testing-auditor) or when debugging a live production issue (use interface-sre-agent).
44
---
55

66
# Runtime Auditor
77

88
Evaluate whether an agent can go from a clean checkout to a safe local runtime or staging-like equivalent, or to the closest safe local simulation of that environment. This skill focuses on install, setup, local services, startup, smoke checks, and infrastructure inspection. It does not require cloud provisioning.
99

10+
## Discipline
11+
12+
This auditor follows code-mint's shared auditor discipline:
13+
14+
- **Depth option** — default `standard`; use `quick` for a sanity check on a recently audited repo or `deep` for legacy codebases, quarterly refreshes, or high-risk readiness claims. Heritage classification from `meta-onboarding` Phase 0 sets a sensible default.
15+
- **Calibration** — every report ends with a Calibration section naming the depth used, confidence level, what was not checked, and what would raise confidence. This is a required artifact, not a disclaimer.
16+
17+
This discipline is inspired by AWS AI-DLC's adaptive-depth and overconfidence-prevention ideas, but code-mint does not vendor or implement the full AI-DLC workflow.
18+
1019
## Collaboration Rules
1120

1221
Do not treat runtime readiness as a pure checklist exercise. Inspect the repository first, then ask only for the operational context the codebase cannot answer confidently.
@@ -57,7 +66,7 @@ Check whether the application dependencies can be installed autonomously:
5766

5867
## Step 2: Evaluate Environment and Configuration Handoff
5968

60-
Cross-reference `autonomy--env-auditor` findings if that report exists.
69+
Cross-reference `autonomy-env-auditor` findings if that report exists.
6170

6271
- [ ] The runtime depends on a documented env loading path
6372
- [ ] Required local or development-safe values are available
@@ -134,7 +143,7 @@ Ensure the report directories exist: `mkdir -p .agents/reports/completed && touc
134143

135144
Ensure `.gitignore` ignores generated report contents while preserving the directories with their `.gitkeep` files.
136145

137-
Write the report to `.agents/reports/autonomy--runtime-auditor-audit.md`:
146+
Write the report to `.agents/reports/autonomy-staging-auditor-audit.md`:
138147

139148
```markdown
140149
# Runtime Audit Report
@@ -189,10 +198,18 @@ Write the report to `.agents/reports/autonomy--runtime-auditor-audit.md`:
189198
- **Current State:** [what exists]
190199
- **Required State:** [what should exist]
191200
- **Recommended Action:** [specific step]
192-
- **Next Skill / Step:** [for example, run `autonomy--runtime-creator`]
201+
- **Next Skill / Step:** [for example, run `autonomy-staging-creator`]
193202

194203
## Next Steps
195-
Run `autonomy--runtime-creator` to remediate findings.
204+
Run `autonomy-staging-creator` to remediate findings.
205+
206+
## Calibration
207+
**Depth:** [quick / standard / deep]
208+
**Confidence:** [High / Medium / Low] — [one-sentence reason]
209+
**Not checked:**
210+
- [specific area + reason]
211+
**To raise confidence:**
212+
- [specific next step]
196213
```
197214

198215
After writing the report, update `docs/onboarding-checklist.md` and `.agents/code-mint-status.json` with the current `smoke_path` outcome status and date. Optionally update `docs/skills-status.md` if the repository keeps the compatibility view.

.agents/skills/autonomy--runtime-auditor/references/smoke-test-guide.md renamed to .agents/skills/autonomy-staging-auditor/references/smoke-test-guide.md

File renamed without changes.

.agents/skills/autonomy--runtime-creator/SKILL.md renamed to .agents/skills/autonomy-staging-creator/SKILL.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,15 @@
11
---
2-
name: autonomy--runtime-creator
3-
description: Builds the scripts, setup flow, and runtime documentation needed for an agent to install dependencies, start local services, boot the app, and run smoke checks from a clean checkout. Use when a runtime audit report exists and runtime readiness needs improvement. Do not use when no audit report exists (run autonomy--runtime-auditor first) or when the main gap is test coverage depth (use autonomy--test-readiness-creator).
2+
name: autonomy-staging-creator
3+
description: Builds the scripts, setup flow, and runtime documentation needed for an agent to install dependencies, start local services, boot the app, and run smoke checks from a clean checkout. Use when a runtime audit report exists and runtime readiness needs improvement. Do not use when no audit report exists (run autonomy-staging-auditor first) or when the main gap is test coverage depth (use autonomy-testing-creator).
44
---
55

66
# Runtime Creator
77

8-
Build out a repository's runtime readiness so that an agent can go from a clean checkout to a runnable application or local runtime equivalent. Base all work on `autonomy--runtime-auditor`.
8+
Build out a repository's runtime readiness so that an agent can go from a clean checkout to a runnable application or local runtime equivalent. Base all work on `autonomy-staging-auditor`.
99

1010
## Prerequisites
1111

12-
Read `.agents/reports/autonomy--runtime-auditor-audit.md`. If no report exists, instruct the user to run `autonomy--runtime-auditor` first.
12+
Read `.agents/reports/autonomy-staging-auditor-audit.md`. If no report exists, instruct the user to run `autonomy-staging-auditor` first.
1313

1414
## Collaboration Rules
1515

@@ -26,7 +26,7 @@ When needed, ask the developer:
2626
- "Which local substitutions are acceptable compared with production?"
2727
- "Which runtime steps are safe to automate, and which must stay manual?"
2828

29-
For smoke-test patterns and safety boundaries, see [../autonomy--runtime-auditor/references/smoke-test-guide.md](../autonomy--runtime-auditor/references/smoke-test-guide.md). The guide lives with the auditor skill intentionally so runtime audit and remediation share one canonical document (`docs/skill-development.md` documents this cross-skill link pattern).
29+
For smoke-test patterns and safety boundaries, see [../autonomy-staging-auditor/references/smoke-test-guide.md](../autonomy-staging-auditor/references/smoke-test-guide.md). The guide lives with the auditor skill intentionally so runtime audit and remediation share one canonical document (`docs/skill-development.md` documents this cross-skill link pattern).
3030

3131
## Step 1: Extract the Handoff Contract
3232

@@ -123,5 +123,5 @@ If any step still depends on human approval or real cloud setup, document that b
123123

124124
## Step 7: Archive
125125

126-
1. Archive the audit report to `.agents/reports/completed/autonomy--runtime-auditor-audit-{YYYY-MM-DD}.md`
126+
1. Archive the audit report to `.agents/reports/completed/autonomy-staging-auditor-audit-{YYYY-MM-DD}.md`
127127
2. Update `docs/onboarding-checklist.md` and `.agents/code-mint-status.json` with the current `smoke_path` outcome status and date. Optionally update `docs/skills-status.md` if the repository keeps the compatibility view.

0 commit comments

Comments
 (0)