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 tarlepp/symfony-flex-backend --skill maintain-ai-guidancegit clone --depth 1 https://github.com/tarlepp/symfony-flex-backendWrote 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/tarlepp/symfony-flex-backend/maintain-ai-guidance)<a href="https://agentmods.dev/skills/tarlepp/symfony-flex-backend/maintain-ai-guidance"><img src="https://agentmods.dev/badge/skills/tarlepp/symfony-flex-backend/maintain-ai-guidance/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/tarlepp/symfony-flex-backend/maintain-ai-guidance"><img src="https://agentmods.dev/badge/skills/tarlepp/symfony-flex-backend/maintain-ai-guidance.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 | $0.00037 | $0.01896 |
| Opus 5.5 | $0.00015 | $0.00758 |
| Sonnet 5.5 | $0.00007 | $0.00379 |
| Haiku 4.5 | $0.00004 | $0.00190 |
Grade A, and why
maintain-ai-guidance 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 yesterday.
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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What is this?
Use this skill when changing repository AI guidance, .github/agents/
profiles, or .github/skills/ workflows and indexes. It covers guidance
ownership, agent permissions and handoffs, and the difference between static
documentation checks and live-client behavior. It does not authorize running
the feature-delivery chain or changing application behavior.
Follow the shared skill guidance, including repository instructions and AI rules. Use update-github-workflows when CI behavior also changes. For executable checker or Make changes, also use maintain-development-tooling.
Table of Contents ᐞ
Guidance map ᐞ
Inspect the affected source and its consumers, not just the requested file:
- README AI inventory: canonical navigation and reading order.
- AGENTS.md: repository-wide actionable requirements; Copilot instructions are its entry point.
- CLAUDE.md: architecture and workflow context.
- AI rules: guidance ownership, recurrence, non-overlap criteria, and CI alignment.
- Skills index and shared guidance: skill format, inventory, and common preparation, validation, and handoff.
- Feature-agent guide and profiles: lead, architect, implementer, and verifier.
scripts/check-skills.py, thecheck-skillsandlint-markdownMake targets, and.github/workflows/main.yml: actual documentation-check coverage and execution environment. Inspectscripts/tests/for existing regression coverage when changing tooling; do not assume every checker already has a test suite.
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.
- yesterday Changed · +6 lines ef62b513a9a4
- 4d ago First seen · 174 lines · 37 tokens per session scan A c04b3e6162e8
maintain-ai-guidance is a skill published in the GitHub repository tarlepp/symfony-flex-backend (288 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,896 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-02.
maintain-ai-guidance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| maintain-ai-guidancetarlepp/symfony-flex-backend | Skill | 288 | yesterday | MIT | A | 37 | Claude Code, Codex |
| api-integration-architectsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 33 | Claude Code |
| dmrwemake-services/django-modern-rest | Skill | 1.5k | today | MIT | A | 80 | Claude Code, Codex |
| horse-database-poolingHashLoad/horse | Skill | 1.4k | 8d ago | MIT | A | 30 | Claude Code, Codex |
| horse-dependency-injectionHashLoad/horse | Skill | 1.4k | 8d ago | MIT | A | 27 | Claude Code, Codex |
| horse-mvc-architectureHashLoad/horse | Skill | 1.4k | 8d ago | MIT | A | 34 | Claude Code, Codex |
| horse-request-responseHashLoad/horse | Skill | 1.4k | 8d ago | MIT | A | 32 | Claude Code, Codex |