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 commands/blightbow/parkour-mcp/releasegit clone --depth 1 https://github.com/blightbow/parkour-mcpWrote 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/commands/blightbow/parkour-mcp/release)<a href="https://agentmods.dev/commands/blightbow/parkour-mcp/release"><img src="https://agentmods.dev/badge/commands/blightbow/parkour-mcp/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 | $0.00018 | $0.02214 |
| Opus 5 | $0.00009 | $0.01107 |
| Sonnet 5 | $0.00004 | $0.00443 |
| Haiku 4.5 | $0.00002 | $0.00221 |
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 3d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walk the user through the parkour-mcp release flow. This stages and tags locally; the user pushes when ready (yubikey required).
Step 1: Preflight
Run these in parallel and report briefly:
git status(working tree must be clean)git log origin/main..HEAD --oneline(show the commits that will ship)uv run cz bump --get-next --yes(next version from commits since last tag)
Abort if working tree is dirty or no commits ahead of origin/main. Flag to the user instead of proceeding.
Also spot-check that every feat: / fix: / refactor: / perf:
commit in the range carries a Why: trailer. Run
git log origin/main..HEAD --format='%h %s%n%(trailers:key=Why,only)'
and flag any commits that are missing one. Why: trailers are the
source of release-note prose; commits without them fall back to the
bare subject which produces weaker changelog entries.
CAVEAT: git's %(trailers) only recognizes trailers in the final
contiguous block of the message. The house style puts a blank line
between Why: and Co-Authored-By:, which splits them, so this command
reports Why: as missing on commits that actually have one. git-cliff
uses its own footer parser and extracts them correctly. Do not act on a
"missing" result here alone — confirm against the Step 2 git-cliff
preview (if the bullet renders as the Why: prose, the trailer is fine;
if it renders as the bare subject, it is genuinely absent).
Step 2: Preview
Show the user what will land:
uv run cz bump --dry-run --yes
LAST_FINAL=$(git tag --list 'v*' --merged HEAD --sort=-v:refname | grep -E '^v[0-9]+\.[0-9]+\.[0-9]+$' | head -1)
git cliff --tag v<NEXT> "$LAST_FINAL..HEAD"
where <NEXT> is the version from step 1. Together these preview the
version bump and the assembled CHANGELOG entry without writing
anything. The range starts at $LAST_FINAL, the most recent final
vX.Y.Z tag, rather than --unreleased: when a release is cut after
intervening RC tags, --unreleased would span only the post-RC
commits, so the final's entry would omit the bulk of the work. Pause;
let the user approve or ask for commit-message edits (via
git commit --amend or git rebase -i) before you stage.
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.
- 3d ago First seen · 181 lines · 18 tokens per session scan A b91ce1c176f8
release is a command published in the GitHub repository blightbow/parkour-mcp (4 stars, last pushed 13d ago), licensed MIT. It adds 18 tokens to every session and 2,214 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 2026-08-31.
Other commands, from other repositories
review-renovate
Review and merge renovate PRs with automerge configuration updates.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
release
Create a full stable release for the project. Optionally pass a title suffix (e.g., "Template Presets Fix") or extra notes.
SHIP_RELEASE
Ship the active release/X.Y.Z — build the installer, merge to main, tag, push, and publish the GitHub release. Run after /prerelease passes.
release
The pre-tag controller: version sync, changelog, clean tree, gate, and suite — every failure listed, the tag printed, never run.
submit_to_list
Fork an external GitHub repo, add an entry to a curated list (e.g. awesome-), and open a PR — all via gh CLI.