security-recipes.ai: Command for GitHub Copilot

.github/prompts/ai-maintenance.md

ai-maintenance is a command for GitHub Copilot from stevologic/security-recipes.ai. It costs 0 tokens per session (542 once invoked), scanned A, original, Apache-2.0.

An automated maintenance task for investigating a failed GitHub Actions workflow. GitHub Actions is GitHub's system for running automated builds, tests, and other repository jobs.

In plain words
What is it for?
Use it to inspect failed workflow logs, reproduce build or test failures, update code when needed, and submit a documented fix.
Why use it?
It gives an agent a defined process for finding the root cause, reproducing the failure, and making the smallest lasting fix instead of patching symptoms.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

This is stevologic/security-recipes.ai's own configuration. It tells GitHub Copilot how to work on security-recipes.ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything security-recipes.ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to stevologic/security-recipes.ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/stevologic/security-recipes.ai/main/.github/prompts/ai-maintenance.md
Clone the repo
git clone --depth 1 https://github.com/stevologic/security-recipes.ai

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for ai-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/commands/stevologic/security-recipes.ai/ai-maintenance.svg)](https://agentmods.dev/commands/stevologic/security-recipes.ai/ai-maintenance)
Your own site
<a href="https://agentmods.dev/commands/stevologic/security-recipes.ai/ai-maintenance"><img src="https://agentmods.dev/badge/commands/stevologic/security-recipes.ai/ai-maintenance.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 542 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00542
Opus 5 $0.00000 $0.00271
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured today against content hash 2ecc80940000, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ai-maintenance 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 today.

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.

.github/prompts/ai-maintenance.md · 50 lines

What it actually says

You are the unattended maintenance engineer for this repository. Read FAILED_WORKFLOW_NAME, FAILED_WORKFLOW_BRANCH, FAILED_WORKFLOW_URL, and FAILED_WORKFLOW_RUN_ID from the environment. Those values identify the failed GitHub Actions run you are repairing. If they are empty, inspect the newest failed run of an automation-critical workflow on main, automation/, or dependabot/ and use that instead.

The workflow "$FAILED_WORKFLOW_NAME" concluded FAILURE on branch "$FAILED_WORKFLOW_BRANCH". Failed run: $FAILED_WORKFLOW_URL (run id $FAILED_WORKFLOW_RUN_ID).

Work the failure end to end:

  1. Inspect it with gh run view $FAILED_WORKFLOW_RUN_ID --log-failed and related recent runs of the same workflow.
  2. Reproduce locally when practical (python -m unittest ..., node --test tests/..., npm run build).
  3. Root-cause it and prefer the smallest durable fix. When a test pins volatile catalog data, convert it to assert the governing policy instead (see the editorial lastmod test in tests/test_cve_landing.py for the established pattern).
  4. If a repository change fixes it: create a branch named automation/ai-fix-, commit with a clear message, push it, open a PR to main that explains root cause, fix, and verification, then enable auto-merge with gh pr merge --auto --squash <pr-number>. The Automation shepherd workflow attaches the required build validation and GitHub completes the merge; never merge directly and never push to main.
  5. If the failure is outside the repository (production droplet, external feeds, registry outages), comment your diagnosis on the open issue labeled automation:production-health, or create that issue if none is open, instead of opening a PR.
  6. If an open automation/ai-fix-* PR already covers the same root cause, push improvements to that PR instead of opening a duplicate.

Constraints: never force-push, never weaken or skip checks and tests to make them pass, never edit unrelated code, and if the root cause remains genuinely unclear after investigation, record your findings on the automation:production-health issue rather than guessing at a fix.

Only act on failures of these workflows: Build, CVE catalog sync, Content refresh, Leftover review, Production watchdog, CVE catalog validation, Automation shepherd, AI issue maintenance, and Search indexing. Ignore successes and ignore failures on unrelated branches.

Changes

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.

  1. today First seen · 50 lines · 0 tokens per session scan A 2ecc80940000

Subscribe to this mod's changes

ai-maintenance is a command published in the GitHub repository stevologic/security-recipes.ai (1 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 542 tokens. 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 2026-09-07.