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 skills/mattflower/tempest/releasenpx skills add MattFlower/tempest --skill releasegit clone --depth 1 https://github.com/MattFlower/tempestWhat 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 | $0.00058 | $0.00825 |
| Opus 5 | $0.00029 | $0.00413 |
| Sonnet 5 | $0.00012 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
release 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 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.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Skill
Cut a new release for Tempest. Follow these steps exactly.
Step 1: Determine the version
- Read
CHANGELOG.mdand review the items under the## Unreleasedsection. - If the Unreleased section has no meaningful entries (only empty headings), stop and tell the user there is nothing to release.
- Based on the scope of changes, suggest a version number following semver. Show the user the summary and your suggested version.
- Ask the user to confirm or provide a different version number. Do not proceed until confirmed.
Step 2: Determine today's date
Run date +%Y-%m-%d to get today's date. Do not guess or hardcode the date.
Step 3: Update CHANGELOG.md
- Replace
## Unreleasedwith## [VERSION] - YYYY-MM-DD(using the confirmed version and today's date). - Immediately after the new version heading and its content, add a fresh Unreleased section with empty subsections:
## Unreleased
### Added
### Fixed
### Changed
### Removed
- Verify the edit looks correct by reading the first 25 lines of CHANGELOG.md.
Step 4: Update the app version
Update the version number in both places it appears:
electrobun.config.ts— change theversionfield in theappobject to the new VERSION.src/bun/pty-manager.ts— change theTERM_PROGRAM_VERSIONvalue to the new VERSION.
Use the Edit tool for both changes.
Step 5: Detect VCS and commit
-
Check whether the repo uses jujutsu or git:
- If
.jjdirectory exists: use jj commands - Else if
.gitdirectory exists: use git commands - NEVER use git commands for commits, bookmarks, or branches in a jj repo.
- If
-
For jujutsu repos:
jj describe -m "Release VERSION" jj new jj bookmark set main -r @- jj git push -
For git repos:
git add CHANGELOG.md git commit -m "Release VERSION" git push
Step 6: Tag the release
- For jujutsu repos:
Then push the tag via git (jj has no tag push support):jj tag set vVERSION -r maingit push origin vVERSION
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 · 104 lines · 58 tokens per session scan A 4cc986e82f23
release is a skill published in the GitHub repository MattFlower/tempest (7 stars, last pushed 25d ago), licensed MIT. It adds 58 tokens to every session and 825 once invoked, about $0.0003 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
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…
map-wayfind
Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
alphafold-database
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.