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 lancewillett/ai-plugins --skill kb-to-specgit clone --depth 1 https://github.com/lancewillett/ai-pluginsWrote 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/lancewillett/ai-plugins/kb-to-spec)<a href="https://agentmods.dev/skills/lancewillett/ai-plugins/kb-to-spec"><img src="https://agentmods.dev/badge/skills/lancewillett/ai-plugins/kb-to-spec.svg" alt="Measured on agentmods" 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 | $0.00110 | $0.01526 |
| Opus 5 | $0.00055 | $0.00763 |
| Sonnet 5 | $0.00022 | $0.00305 |
| Haiku 4.5 | $0.00011 | $0.00153 |
Grade A, and why
kb-to-spec 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 7d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kb-to-spec
Turn one of your private Markdown notes or KB files into a shareable spec committed to a project's GitHub repo—repeatably, without leaking anything private and without duplicating content.
The two-file model
After promotion there are two files, independent, no shared text:
| File | Lives in | Holds | Who sees it |
|---|---|---|---|
| Spec | the project repo (<repo>/docs/...) |
the shareable design content, standalone—a reader needs nothing else | anyone with repo access |
| Private note | your local notes / KB (where it already is) | private-only material—logs, decisions-in-progress, personal meta, internal cross-refs—plus a link up to the spec | only you |
Never duplicate. If a piece of content is shareable, it lives in the spec, and the private note links to it instead of repeating it. The private note is a thin private layer on top of the spec, not a copy of it.
Inputs
- Source: the private note or KB file to promote (path; ask if not given).
- Target repo: your local clone of the target repo (ask if unknown).
- Spec location: detect the repo's existing convention—look for an existing
docs/**/specs/dir and a sample spec. Match what's already there (path + whether specs use YAML frontmatter or a bold**Authors:**header). The Authors field is the de-facto ownership key: every spec lists its real authors, and editing rights follow it.
Procedure
1. Read source and learn the repo's spec convention
Read the private file. In the target repo, find an existing spec and note: where specs
live, the header style (frontmatter vs. inline **Date/Status/Authors:**), and the
filename pattern (e.g. YYYY-MM-DD-<slug>.md).
2. Classify the content
Split the private file into:
- Shareable → design, decisions, architecture, rationale, scope, open questions that a teammate needs.
- Private-only → keep in the note: personal meta ("my lane", who-owns-what framing), internal cross-references that only resolve in your local file system (e.g. links to other private notes), log entries, draft messages, anything that only makes sense inside your own environment.
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.
- 7d ago First seen · 108 lines · 110 tokens per session scan A ab1ba650117c
kb-to-spec is a skill published in the GitHub repository lancewillett/ai-plugins (2 stars, last pushed 22d ago), licensed MIT. It adds 110 tokens to every session and 1,526 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".