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 instructions/netopsengineer/agent-skill-description-optimizer/agents-mdgit clone --depth 1 https://github.com/netopsengineer/agent-skill-description-optimizerWhat 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 | $0.04889 | $0.04889 |
| Opus 5 | $0.02445 | $0.02445 |
| Sonnet 5 | $0.00978 | $0.00978 |
| Haiku 4.5 | $0.00489 | $0.00489 |
Grade C, and why
agent-skill-description-optimizer AGENTS.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Clean up: `rm -rf "$SCRATCH"`. How it starts
The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent execution contract for this repo. Human explanation is canonical in README.md;
reference it rather than duplicating it, and keep operator narration out of this file.
Purpose
Optimize a skill's description: frontmatter (the text that gates skill invocation).
Evaluation and improvement both run through claude -p, so no ANTHROPIC_API_KEY is
required. Entry point: optimize_description_v2.py (shim over the src/skill_optimizer/
package). Runtime: Python standard library only; interpreter floor Python 3.14+.
Invoke
Canonical cross-repo call (project-targeted uv pins the 3.14 interpreter):
uv run --project /ABSOLUTE/PATH/TO/agent-skill-description-optimizer \
optimize-skill-description \
--eval-set /ABSOLUTE/PATH/TO/eval.json \
--skill-path /ABSOLUTE/PATH/TO/skill \
--model MODEL_ID --report none --max-iterations 5 --verbose
- Pass
--report nonefor every headless run: stdout stays a single JSON object and no browser opens. Mandatory for a stdout-parsing caller. - Parse stdout as JSON; read
best_description. - Apply it to the skill's
SKILL.mdfrontmatter, or pass--writeto apply it automatically (backs up toSKILL.md.bak; refuses an over---max-desc-charswinner). - Treat stderr as progress only — tail it, never parse it.
Equivalent in-repo forms: uv run optimize-skill-description ..., uv run python -m skill_optimizer ..., uv run python optimize_description_v2.py .... Direct execution
requires a named 3.14+ interpreter (python3.14 optimize_description_v2.py ...). Full
flag list: README.md.
Preconditions
Checked at startup, before any token spend or artifact write. Each failure exits 1 with a
one-line stderr message and empty stdout (a stdout-parsing caller fails legibly, never on
a JSONDecodeError or mid-run traceback):
| Condition | Failure message prefix |
|---|---|
claude on PATH and executable |
claude CLI not found or not executable: |
| Interpreter is Python >=3.14 | Requires Python >=3.14; |
| Eval set well-formed | Invalid eval set: |
| Holdout split satisfiable | Invalid holdout split: |
--out and --results-dir not both set |
--out and --results-dir are mutually exclusive |
--iterations in [0, 50] |
--iterations must be between 0 and 50 |
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 First seen · 385 lines · 4,889 tokens per session scan C 4aefe38b595a
agent-skill-description-optimizer AGENTS.md is an instructions file published in the GitHub repository netopsengineer/agent-skill-description-optimizer (2 stars, last pushed 4d ago), licensed MIT. It adds 4,889 tokens to every session, about $0.0244 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ClawBench AGENTS.md
Instructions for TIGER-AI-Lab/ClawBench, covering clawbench -- agent context, what this is, project structure, setup and 2. configure at least one model.
yao-meta-skill AGENTS.md
Instructions for yaojingang/yao-meta-skill, covering agent instructions, project map, verification, trusted evidence runs and boundaries.
langium-ai CLAUDE.md
Instructions for eclipse-langium/langium-ai, covering claude.md, project overview, commands, build & test (all workspaces) and lint & format.
proofloop CLAUDE.md
Instructions for sattyamjjain/proofloop, covering claude.md, v4.3 scope contract (2026-05-03), build & development commands, architecture and data flow.
Aeon-Bench-Pod AGENTS.md
Instructions for AEON-7/Aeon-Bench-Pod, covering agents.md — aeon bench pod operating manual for ai agents, the short version — this is the whole job, 0. detail on those four steps, 1. what aeon bench is and 2. install on any platform.
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.