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/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsnpx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-readmeWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-readme)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-readme"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-readme/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-readme"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-readme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 8 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00025 | $0.05132 |
| Opus 5 | $0.00013 | $0.02566 |
| Sonnet 5 | $0.00005 | $0.01026 |
| Haiku 4.5 | $0.00003 | $0.00513 |
Grade A, and why
sk-create-readme 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 8d 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create README (workflow)
create-readme is the README authoring packet in the sk-doc family. It writes current-state folder READMEs and install guides from local evidence, using packet-local templates under assets/ and shared create-quality-control validators under ../shared.
1. WHEN TO USE
Activation Triggers
Use this packet when the request involves:
- Creating or refreshing a folder
README.md. - Documenting a project, skill, feature, component or source-code directory.
- Writing developer orientation for a code folder, including topology, boundaries, entrypoints and validation.
- Creating an install guide for MCP servers, plugins, CLI tools or development dependencies.
- Running
/create:readme.
Keyword triggers: create readme, /create:readme, readme, folder readme, write readme, README.md, front-page overview, install guide, installation guide, setup guide, getting our project running, running from scratch, code folder readme.
When NOT to Use
Use another sk-doc packet when:
- The user wants to audit, validate, score, or optimize an existing README or another existing document without authoring or refreshing it. Use
create-quality-control. - The user wants to scaffold a skill, agent, command, benchmark package, feature catalog, testing playbook, flowchart, or changelog. Use
create-skill,create-agent,create-command,create-benchmark,create-feature-catalog,create-manual-testing-playbook,create-flowchart, orcreate-changelog. - The target is not markdown.
- The folder is self-explanatory and a parent README or inline comments already give enough orientation.
This is a nested workflow packet under the sk-doc parent hub. It owns README and install-guide authoring only. It does not carry graph-metadata.json; advisor identity, skill graph metadata and cross-packet routing live at the sk-doc hub root.
What ships with it
23 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.
- assets/install-guide-template.md 26 KB
- assets/readme-code-template.md 17 KB
- assets/readme-template.md 8.6 KB
- changelog/v1.0.0.0.md 2.0 KB
- changelog/v1.1.0.0.md 1.8 KB
- manual-testing-playbook/artifact-routing/self-explanatory-folder-stays-unchanged.md 5.2 KB
- manual-testing-playbook/artifact-routing/skill-readme.md 5.0 KB
- manual-testing-playbook/evidence-and-shape/code-folder-navigation-shape.md 5.3 KB
- manual-testing-playbook/evidence-and-shape/evidence-first-current-state.md 5.2 KB
- manual-testing-playbook/install-guide/five-phase-install-flow.md 5.7 KB
- manual-testing-playbook/install-guide/one-line-install-stays-inline.md 5.2 KB
- manual-testing-playbook/manual-testing-playbook.md 11 KB
- README.md 9.8 KB
- references/install-guide/quality-and-standards.md 4.2 KB
- references/install-guide/section-examples.md 3.9 KB
- references/README.md 4.2 KB
- references/readme/quality-and-checklist.md 5.2 KB
- references/readme/types-and-voice.md 4.1 KB
- references/readme/writing-patterns.md 7.6 KB
- scripts/audit_readmes.py 38 KB runs code
- scripts/check_derived_readme_counts.py 9.7 KB runs code
- scripts/check_readme_references.py 9.6 KB runs code
- scripts/README.md 1.4 KB
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.
- 8d ago First seen · 485 lines · 25 tokens per session scan A b5abb270e52b
sk-create-readme is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 5,132 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.