Skip to content

fix(grant-scout): stop fabricated prior-grant claims; de-hardcode metrics #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Oba-One wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix(grant-scout): stop fabricated prior-grant claims; de-hardcode metrics #19

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e7bd614
fix(grant-scout): stop fabricated prior-grant claims; de-hardcode met…
Oba-One May 31, 2026
2715642
fix(grant-scout): add claim-verification guardrail + de-hardcode metrics
Oba-One May 31, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions routines/claude/guild-grant-scout.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ This routine is **centered on three primary funding targets — Coop, Green Good

What this guild is uniquely positioned to win funding for:

- **Green Goods** — offline-first regenerative documentation platform. Passkey auth, EAS attestations, Arbitrum production deployment with real users (Season One: 13 live gardens), Envio indexer. Strongest grant evidence in the guild — production code + production users.
- **Green Goods** — offline-first regenerative documentation platform. Passkey auth, EAS attestations, Arbitrum production deployment with real users (Season One pilot live on Arbitrum mainnet), Envio indexer. Strongest grant evidence in the guild — production code + production users.
- **Coop** — browser extension and PWA for group knowledge capture; Yjs CRDT, Filecoin archival, Safe multisig, **shares Green Goods identity + attestation infrastructure**. Cross-project leverage is real, not aspirational.
- **PGSP** — Public Goods Staking Protocol. Hoodi testnet onboarding, Lido CSM v3 readiness, validator squad operator support.
- **Cookie Jar** — funding allowance primitive. DAO tooling, local capital allocation, funding infrastructure.
Expand All @@ -59,7 +59,7 @@ What this guild is uniquely positioned to win funding for:

**Distinct angles for funder pitches:** offline-first PWA infrastructure for low-connectivity contexts, on-chain regenerative impact attestation, shared identity primitives across multiple production products, real-user pilot data (Season One gardens on Arbitrum mainnet), evaluator/operator role separation as a governance pattern.

Prior grant work to reference (do not duplicate, iterate): NLnet NGI Zero Commons "Evidence Commons", Octant proposal packs, OSV Grant proposal (Drive), and any Drive docs under grants/proposals.
Prior grant *materials* to reference for reuse (iterate, do not duplicate): the NLnet NGI Zero Commons draft(s), Octant proposal packs, the OSV Grant proposal, and any Drive docs under grants/proposals. **These are application materials, not awards — never describe them as won, completed, delivered, or as a prior funding relationship unless verified (see Guardrails).** Authoritative funding status lives in the grants ledger (`database-export.csv`, Drive `Funding database export` folder): only rows marked **Completed** are wins. As of 2026-05-31: **NLnet = Applied / pending, never awarded** (no prior NLnet grant or relationship exists — do not imply one); OSV = submitted/awaiting; completed wins citable as track record = Grant Ships R1/R2, Gitcoin GG20–24, Octant Epoch 5 & 10 (Epoch 12 accepted), ReFi-in-Arbitrum, Arbitrum DAO "Building Regenerative Impact".

## Phase 0: Prior-run recall

Expand Down Expand Up @@ -440,6 +440,8 @@ If the Drive write fails, still consider the run successful (Discord post + Line
- **One full draft per run max.** Lightweight outlines for additional urgent opportunities are fine.
- **Never submit proposals.** Human review owns final submission.
- **Only claim capabilities that exist in the code today.** Planned work must be labeled as proposed.
- **Verify factual claims against primary sources before they enter a draft or a Linear Issue.** Track record, prior funding, partnerships, "live" capabilities, and metrics must each trace to a primary source — the grants ledger (`database-export.csv`) for funding status, the indexer/PostHog for metrics, repo code for capabilities. If a claim can't be verified, omit it or mark it "unverified — confirm before submission." Never upgrade an "applied"/"in progress" item to "awarded"/"completed," and never imply a funder relationship the ledger doesn't show. A fabricated track-record claim is a credibility risk with funders and a disqualifier with several (incl. NLnet).
- **Never hardcode production metrics in a draft.** Garden/gardener/operator/evaluator counts and similar figures drift between runs — pull them from the indexer/PostHog at run time and cite with an "as of {date}" stamp.
- **Don't share sensitive metrics, unannounced strategy, private counterparties, or budget details in Discord.** Those go to Drive + Linear.
- **Do not modify source files in any project repo or edit Miro boards or Canva designs.** All design-surface reads are read-only.
- **PostHog is privacy-public mode only.** Never paste replay URLs, session IDs, distinct IDs, wallet addresses, or any private field. Curated question names only — no raw HogQL in the routine reasoning.
Expand Down