Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tarlepp/symfony-flex-backendnpx agentmods add skills/tarlepp/symfony-flex-backend/maintain-development-toolingWrote 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-development-tooling)<a href="https://agentmods.dev/skills/tarlepp/symfony-flex-backend/maintain-development-tooling"><img src="https://agentmods.dev/badge/skills/tarlepp/symfony-flex-backend/maintain-development-tooling/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-development-tooling"><img src="https://agentmods.dev/badge/skills/tarlepp/symfony-flex-backend/maintain-development-tooling.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 | $0.00036 | $0.02388 |
| Opus 5.5 | $0.00014 | $0.00955 |
| Sonnet 5.5 | $0.00007 | $0.00478 |
| Haiku 4.5 | $0.00004 | $0.00239 |
Grade A, and why
maintain-development-tooling 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 2d 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 — 208 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 development scripts, Make targets, checker behavior, command routing, or script regression tests. It owns tooling behavior, not dependency upgrades or application features. Use update-github-workflows for CI job behavior, update-github-actions for action pins, and update-docker-images for image inspection and pins. Use maintain-ai-guidance for skill and instruction contracts rather than expanding a checker to impose new policy implicitly.
Follow the shared skill guidance, including repository instructions and AI rules.
Table of Contents ᐞ
Tooling path map ᐞ
Inspect the implementation and its actual callers:
Makefile: host-target allowlist, forwarding, Compose selection, environment propagation, help, task recipes, runner/report paths, and exit decoration.- Scripts guide and scripts in
scripts/: documentation checking, action/tool update discovery, workflow validation, Docker image helpers, and project statistics. scripts/tests/make-container-test.sh,scripts/tests/docker-images-test.sh, andscripts/tests/check-workflow-tool-updates-test.py: existing offline fixtures, command mocks, failure assertions, and temporary-file handling. Do not assume every script already has a regression suite..github/workflows/and.github/actions/: direct and Make-mediated callers, inputs, invocation environment, and consumers of output and exit status.Dockerfile,docker/ci-compose.yaml,.devcontainer/, and tool manifests when affected: available interpreters, executables, paths, and mounts.- Command reference, testing guide, and CI guide: documented commands, validation scope, and reproduction instructions.
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.
- 2d ago Changed · +18 lines 6ee252536f19
- 3d ago Changed · +11 lines 951b081db9bb
- 4d ago First seen · 179 lines · 36 tokens per session scan A 979f6e1eedcb
maintain-development-tooling is a skill published in the GitHub repository tarlepp/symfony-flex-backend (288 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 2,388 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-development-tooling compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| maintain-development-toolingtarlepp/symfony-flex-backend | Skill | 288 | yesterday | MIT | A | 36 | 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 |