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 chf3198/copilot-governance --skill workflow-self-annealgit clone --depth 1 https://github.com/chf3198/copilot-governanceWrote 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/chf3198/copilot-governance/workflow-self-anneal)<a href="https://agentmods.dev/skills/chf3198/copilot-governance/workflow-self-anneal"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/workflow-self-anneal/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/chf3198/copilot-governance/workflow-self-anneal"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/workflow-self-anneal.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 | $0.00046 | $0.01166 |
| Opus 5 | $0.00023 | $0.00583 |
| Sonnet 5 | $0.00009 | $0.00233 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
workflow-self-anneal 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 9d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Self-Anneal
Purpose
Perform a controlled, auditable improvement pass on instructions and process docs to reduce repeated failures while preserving human control.
This skill optimizes process reliability, not model internals.
Hard safety constraints
- No unbounded loops or autonomous "improve forever" behavior.
- Max one anneal pass per invocation; max three proposed doc changes.
- No deploy/publish success claims without verification evidence.
- Do not modify security/permission policy automatically; propose only.
- If evidence insufficient, return
NO_CHANGEwith missing-evidence list.
Trigger conditions
- Same failure pattern ≥2 times in 7 days.
- Session crash/restart/tooling instability.
- Instructions contradicted by observed actions.
- Pre-merge gate requires hardening evidence.
- Repeated carryover/blocked items across iterations.
- PR/merge latency breaches targets or reopened issues trend up.
- Commits exist without linked GitHub issues (process drift).
- Consultant check registry returns ≥1 FAIL on domain:governance.
- Fleet check
fleet-002(cost-budget) FAIL for ≥2 consecutive cycles.
Consultant Integration
Self-anneal may be invoked automatically from consultant-feedback.js when gov-002 (baton-artifact-presence) or gov-003 (event-emission) FAIL — these are workflow process failures, not implementation bugs.
Check IDs are managed in scripts/global/consultant-checks.js (3 domains: governance/tools/fleet).
Input collection
Collect: execution artifacts (logs, errors, checks), instructions/workflow docs, recent commits/PR notes. If unavailable, declare missing and stop.
Analysis protocol
- Detect mismatch: expected vs observed behavior.
- Classify root cause:
ambiguity|missing guardrail|stale instruction|tool fragility|human override. - Assess recurrence risk:
low|medium|highby frequency and blast radius. - Detect Agile drift signals: carryover, blocked age, review/merge latency, reopen rate.
- Ticket linkage:
git log --oneline | wc -lvs--grep='#'. If <80%, flagticket-linkage-drift. - PR coverage: commits vs
gh pr list --state all. If 0 PRs, flagpr-coverage-drift. - Event gaps: count events in
.dashboard/events.jsonlper role transition. If <1 event per baton handoff, flagevent-emission-drift.
- Ticket linkage:
- Propose minimal fix: smallest docs/workflow delta preventing recurrence.
- Define verification gate: objective checks confirming the fix.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 99 lines · 46 tokens per session scan A 7811e87da785
workflow-self-anneal is a skill published in the GitHub repository chf3198/copilot-governance (1 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,166 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…