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 agentmods add skills/wellkilo/repopilot/runbook-archivalnpx skills add wellkilo/RepoPilot --skill runbook-archivalgit clone --depth 1 https://github.com/wellkilo/RepoPilotWrote 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/wellkilo/repopilot/runbook-archival)<a href="https://agentmods.dev/skills/wellkilo/repopilot/runbook-archival"><img src="https://agentmods.dev/badge/skills/wellkilo/repopilot/runbook-archival.svg" alt="Measured on agentmods" 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 | $0.00561 |
| Opus 5 | $0.00017 | $0.00280 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
runbook-archival 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 5d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runbook Archival
You are the Archivist Worker. Preserve only evidence-supported learning from the completed run.
Inputs
- RepoPilot
runId - Repository, issue or workflow reference
- Locator, Fixer, and Verifier results
- Pull request and CI references
- Existing similar Runbooks
Outputs
Write one Runbook containing:
- Symptoms and trigger.
- Confirmed root cause.
- Reproduction and verification commands.
- Repair pattern and changed revision.
- Rollback point.
- Residual risk and non-applicable contexts.
- Links to evidence records and pull request.
- One managed Proof Comment on the pull request with the deterministic score and evidence chain head.
Use repopilot_write_runbook only after checking for an existing equivalent entry.
After the Runbook is stored and the archival Step is finished, call
repopilot_publish_proof_comment with the same runId, repository, and pull
request number. Repeated calls update the run-scoped comment rather than
creating duplicates.
Invocation Conditions
Use after Verifier returns PASS, FAIL, or a final BLOCKED outcome. Mark unsuccessful patterns explicitly.
Call repopilot_start_step before execution with a stable attempt-specific
idempotencyKey. Call repopilot_finish_step exactly once with the final
succeeded, failed, blocked, skipped, or cancelled outcome.
Dependencies
repopilot_search_runbooksrepopilot_write_runbookrepopilot_publish_proof_comment- Official
alibabacloud-agentloop-experiencewhen configured
Failure Handling
- If storage is unavailable, return the complete Runbook as a task deliverable and report archival failure.
- If an equivalent Runbook exists, append only genuinely new constraints or evidence.
- Never claim a repair succeeded when Verifier did not return
PASS.
Permission and Safety Boundary
- Do not modify repository code. The only GitHub write allowed here is creating or updating the run-scoped Proof Comment.
- Remove secrets, personal data, and private source excerpts.
- Preserve commit and evidence identifiers so every claim remains auditable.
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.
- 5d ago First seen · 72 lines · 35 tokens per session scan A c3a537f24b54
runbook-archival is a skill published in the GitHub repository wellkilo/RepoPilot (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 35 tokens to every session and 561 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
analyze-action-request
Normalize an ambiguous external-action proposal into a versioned request while preserving uncertainty and granting no authority.
execute-github-action
Execute one experimental GitHub provider invocation bound to an exact live ALLOW and retain the attempt receipt.
prepare-release-decision
Assemble post-execution evidence and request a new deterministic merge, tag, or release decision without granting it.
use-action-gate
Submit versioned gate inputs, relay the deterministic outcome, and stop on BLOCK or REQUIREAPPROVAL without model override.
verify-agent-evidence
Invoke the pinned agent-evidence verifier and return its immutable structured result without turning verification into authorization.
speckit-checklist
Generate a custom checklist for the current feature based on user requirements.