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/coleam00/archon/releasenpx skills add coleam00/Archon --skill releasegit clone --depth 1 https://github.com/coleam00/ArchonWrote 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/coleam00/archon/release)<a href="https://agentmods.dev/skills/coleam00/archon/release"><img src="https://agentmods.dev/badge/skills/coleam00/archon/release.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 | $0.00093 | $0.09599 |
| Opus 5 | $0.00046 | $0.04799 |
| Sonnet 5 | $0.00019 | $0.01920 |
| Haiku 4.5 | $0.00009 | $0.00960 |
Grade C, and why
release scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TMP_DIR" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Also run `/test-release curl-mac x.y.z` to cover the curl install path. The two install paths test slightly different things (Homebrew tests the tap formula, curl tests `install.sh` and checksums from the release) and bo How it starts
The opening of the file, as written. The whole thing — 789 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Skill
Creates a release by comparing dev to main, generating changelog entries from commits, bumping the version, and creating a PR. After the tag is pushed and the release workflow finishes building binaries, updates the Homebrew formula with the real SHA256 values from the published checksums.txt, syncs the coleam00/homebrew-archon tap, and verifies the end-to-end install path via /test-release.
⚠️ CRITICAL — Homebrew formula SHAs cannot be known until after the release workflow builds binaries.
The
versionfield inhomebrew/archon.rband thesha256fields must be updated atomically. Never update one without the other.The correct sequence is:
- Tag is pushed → release workflow fires → binaries built →
checksums.txtuploaded- Fetch
checksums.txtfrom the published release- Parse the SHA256 per platform
- Update
homebrew/archon.rbwith the new version AND the new SHAs in a single commit- Sync to the
coleam00/homebrew-archon/Formula/archon.rbtap repoUpdating the formula's
versionfield without also updating thesha256values creates a stale, misleading formula that looks valid but produces checksum mismatches on install. This has happened before (v0.3.0: version updated to 0.3.0 but SHAs were still from v0.2.13). Always do both or neither.
Process
Step 1: Validate State
# Must be on dev branch with clean working tree
git checkout dev
git pull origin dev --no-rebase
git status --porcelain # must be empty
git fetch origin main
If not on dev or working tree is dirty, abort with a clear message.
Then check that dev actually contains main. Anything committed directly to main — a docs typo fix, a hotfix, the previous release's formula commit — stays stranded there until someone merges it back. The release PR would then propose reverting it, and the next release inherits the drift.
if git merge-base --is-ancestor origin/main origin/dev; then
echo "dev contains main — OK"
else
echo "DRIFT: commits exist on main that dev does not have:"
git log origin/dev..origin/main --oneline
echo ""
echo "Resync before releasing:"
echo " git checkout dev && git pull origin main --no-rebase && git push origin dev"
exit 1
fi
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.
- today First seen · 789 lines · 93 tokens per session scan C b7c78eb53801
release is a skill published in the GitHub repository coleam00/Archon (23,361 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 9,599 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
greet
A greeting skill for testing.
mcp-setup
Configure MCP servers via a guided menu — curated bundles (Context7, Exa, Filesystem, GitHub) or a custom stdio/HTTP server — using tinycode mcp add, with scope control, verification, and troubleshooting guidance.
team
Launch a multi-agent team to work on a task in parallel.