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 mishahanin/heading-os --skill skill-creatorgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/mishahanin/heading-os/skill-creator)<a href="https://agentmods.dev/skills/mishahanin/heading-os/skill-creator"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/skill-creator/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/mishahanin/heading-os/skill-creator"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/skill-creator.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 | $0.00076 | $0.03977 |
| Opus 5 | $0.00038 | $0.01988 |
| Sonnet 5 | $0.00015 | $0.00795 |
| Haiku 4.5 | $0.00008 | $0.00398 |
Grade C, and why
skill-creator 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Explanatory: this section IS the reasoning it asks the model to adopt, and it argues against rigid instruction shapes in its own third point. Per .claude/rules/documentation-style.md, flattening it destroys the poin How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
A skill for creating new skills and iteratively improving them.
At a high level, the process of creating a skill goes like this:
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and run claude-with-access-to-the-skill on them
- Help the user evaluate the results both qualitatively and quantitatively
- While the runs happen in the background, draft some quantitative evals if there are none. Use any that exist as they are, or modify them where something needs to change. Then explain them to the user.
- Run
eval-viewer/generate_review.pyto show the user the results and the quantitative metrics
- Rewrite the skill from the user's evaluation of the results. Also fix any glaring flaw that the quantitative benchmarks make apparent.
- Repeat until you're satisfied
- Expand the test set and try again at larger scale
Find out where the user stands in this process, then help them through the remaining stages. Say they open with "I want to make a skill for X". Narrow down what they mean, write a draft, write the test cases, agree how to evaluate, run the prompts, and repeat.
On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.
Stay flexible. If the user says "I don't need a bunch of evaluations, just vibe with me", do that instead.
Once the skill is done, and the order here is flexible too, run the skill description improver. A separate script owns it, and it optimizes how the skill triggers.
Cool? Cool.
Communicating with the user
The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of Claude is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.
What ships with it
22 files 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.
- agents/analyzer.md 2.4 KB
- agents/comparator.md 1.7 KB
- agents/grader.md 5.6 KB
- assets/eval_review.html 6.9 KB
- eval-viewer/generate_review.py 18 KB runs code
- eval-viewer/viewer.html 46 KB
- license.txt 11 KB
- references/anthropic-skill-spec.md 5.2 KB
- references/description-optimization.md 5.7 KB
- references/platform-specific.md 3.9 KB
- references/running-evals.md 7.7 KB
- references/schemas.md 12 KB
- scripts/__init__.py 0 B runs code
- scripts/aggregate_benchmark.py 18 KB runs code
- scripts/generate_report.py 13 KB runs code
- scripts/improve_description.py 13 KB runs code
- scripts/init_skill.py 13 KB runs code
- scripts/package_skill.py 4.7 KB runs code
- scripts/quick_validate.py 6.6 KB runs code
- scripts/run_eval.py 19 KB runs code
- scripts/run_loop.py 16 KB runs code
- scripts/utils.py 1.6 KB runs code
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.
- 9d ago First seen · 292 lines · 76 tokens per session scan C c293d7544057
skill-creator is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 76 tokens to every session and 3,977 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.