Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Gesondian/ai-collab-governance-skills --skill uat-reopen-intakegit clone --depth 1 https://github.com/Gesondian/ai-collab-governance-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gesondian/ai-collab-governance-skills/uat-reopen-intake)<a href="https://agentmods.dev/skills/gesondian/ai-collab-governance-skills/uat-reopen-intake"><img src="https://agentmods.dev/badge/skills/gesondian/ai-collab-governance-skills/uat-reopen-intake/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gesondian/ai-collab-governance-skills/uat-reopen-intake"><img src="https://agentmods.dev/badge/skills/gesondian/ai-collab-governance-skills/uat-reopen-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00588 |
| Opus 5 | $0.00017 | $0.00294 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
uat-reopen-intake scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UAT Reopen Intake
Core Principle
When a user challenges an accepted result, the AI must not directly fix, directly re-accept, or silently widen the acceptance scope. It must first decide what failed, what evidence is missing, and who owns the smallest next action.
Required Inputs
- Original receipt or acceptance summary.
- User challenge or reopen reason.
- Evidence actually covered by the original receipt.
- Current failing signal, if any.
- Candidate owner or lane, if known.
Intake Flow
- Run
accepted_scope_recheck: list the route, surface, viewport, data, assertion level, fact source, and receipt identity that were actually covered. - Identify the
failed_gate_mincandidate: the smallest reproducible gate that contradicts the prior acceptance. - Classify
failure_type:missing_evidencescope_overclaimreal_regressionowner_boundary_unclearenvironment_or_harness_gapuser_expectation_delta
- Record
missing_evidence: what proof is required before any new acceptance claim. - Make
next_owner_decision: who should act next, and what exact gate they must satisfy.
Allowed Verdicts
| Verdict | Meaning |
|---|---|
reopen_required |
The challenge exposes a real gap in the prior acceptance scope. |
needs_failed_gate_min |
The challenge is plausible but lacks the smallest reproducible failing gate. |
needs_evidence |
The request needs more evidence before ownership or acceptance can be decided. |
reroute_owner |
The issue belongs to a different owner based on mechanism attribution. |
no_reopen_from_current_evidence |
Current evidence does not contradict the prior bounded receipt. |
Output Contract
verdict:
accepted_scope_recheck:
failed_gate_min_candidate:
failure_type:
missing_evidence:
next_owner_decision:
return_owner_on_fail:
must_not_claim:
remaining_risks:
Common Mistakes
- Treating a user challenge as permission to immediately patch code.
- Saying
acceptedagain without re-checking what was originally covered. - Using a broad complaint as proof that all related surfaces failed.
- Assigning owner based only on the file where code lives.
- Collapsing environment or harness gaps into product failure.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 69 lines · 35 tokens per session scan A c857a8a2bc65
uat-reopen-intake is a skill published in the GitHub repository Gesondian/ai-collab-governance-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 588 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
quality-control-workflow
Construction quality control workflow automation. Manage QC inspections, track defects, generate NCRs, and ensure specification compliance throughout the project.
user-story
Create user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.
cro
Conversion audit for funnels and pages — a section-by-section friction log (clarity, anxiety, distraction, motivation), heuristic checks (message match, above-the-fold value prop, form cost), an ICE-scored hypothesis backlog, and top-3 A/B test designs with success metrics and minimum-sample notes. Use when the user…
acceptance-orchestrator
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
nextjs-testing
Write Jest or Vitest unit tests with React Testing Library and Playwright E2E tests for Next.js projects. Use when testing components with RTL, mocking APIs with MSW, or creating Playwright user flow tests.
red-team
Red Team persona for Business Logic and Auth manipulation. Generates and executes stateful fuzzing scripts (Playwright/Python) to test RBAC bypasses, BOLA/IDOR, race conditions, and complex multi-step transaction flaws.