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 meganemura/headsign --skill improve-project-skillgit clone --depth 1 https://github.com/meganemura/headsignWrote 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/meganemura/headsign/improve-project-skill)<a href="https://agentmods.dev/skills/meganemura/headsign/improve-project-skill"><img src="https://agentmods.dev/badge/skills/meganemura/headsign/improve-project-skill/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/meganemura/headsign/improve-project-skill"><img src="https://agentmods.dev/badge/skills/meganemura/headsign/improve-project-skill.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 | $0.00044 | $0.00333 |
| Opus 5.5 | $0.00018 | $0.00133 |
| Sonnet 5.5 | $0.00009 | $0.00067 |
| Haiku 4.5 | $0.00004 | $0.00033 |
Grade A, and why
improve-project-skill 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 27d 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.
What it actually says
Improve a project-local skill
Read references/procedure.md to locate the source, assess the evidence, and verify a revision. Choose changes by their expected effect on the user's outcome. A useful method can stay with a reason.
Keep objectives, constraints, available gates, and authority clear. Let the working agent choose the method. Preserve requested outcomes, explicit budgets, required reviews and approvals, and the user's ability to stop. Use existing task authority; ask only when missing information or authority affects the result.
Include responsibility to assess the method when feedback exposes a weakness, and at completion. The working agent chooses useful repairs or justified retention within remaining budget. It applies repairs to the current work, verifies affected results, and preserves useful lessons. Assessment must not become recursive improvement work or enlarge the task budget.
After a verified revision, use any feedback route the user has configured for reusable findings. Generalize sensitive material before crossing its information boundary. Report delivery separately from adoption; continue authorized work without waiting for an upstream reply. Feedback does not require a new service.
Finish after the authorized revision and appropriate verification. Report the change, evidence, and remaining gaps. If the user requested a trial or ongoing work, continue that authorized work; revising its skill does not complete it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 27d ago Changed · +5 lines cebe9075df6b
- 29d ago First seen · 30 lines · 44 tokens per session scan A e694f56722e2
improve-project-skill is a skill published in the GitHub repository meganemura/headsign (1 stars, last pushed 28d ago), licensed MIT. It adds 44 tokens to every session and 333 once invoked, about $0.0002 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 2026-10-01.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
context-exclusion
Maintain .agent-no-read.md markers for approved generated directories using deterministic scripts. Use when configuring generated-code context exclusion or restoring markers after regeneration, not for ordinary ignore rules or OS permissions.
context-lifecycle
Author, review, or integrate Agent Context Lifecycle Protocol V1 declarations and adapters. Use for explicit ephemeral messages, persistent named blocks, trusted discard controls, or agent compatibility questions; do not claim Codex itself can rewrite prior request history.
creating-workflows
A guide for creating reusable JavaScript workflows that coordinate several helper agents through steps, loops, parallel tasks, and summaries.
subagent-driven-development
Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
openspec
A specification-driven development process that records proposed software changes, implementation tasks, and updates to the project’s current behavior specifications.