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/marcus/sidecar/release-sidecarnpx skills add marcus/sidecar --skill release-sidecargit clone --depth 1 https://github.com/marcus/sidecarWhat 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 | $0.00053 | $0.01414 |
| Opus 5 | $0.00026 | $0.00707 |
| Sonnet 5 | $0.00011 | $0.00283 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
release-sidecar 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing a New Version
Operator contract: docs/guides/active/releasing.md. Enforcement lives in scripts/ and
BUMP=minor make release (or RELEASE_VERSION=vX.Y.Z make release for an explicit
version). Prefer the one-shot command over replaying this checklist by hand.
Prerequisites
- Go matching
go.mod - Clean working tree;
mainidentical to liveorigin/main - Tests and Go CI green on the commit you will tag (tests and lint) —
check-release-state.shnow checks this itself viagh run list --workflow=go-ci.ymland fails closed if it's red/running/missing, so you don't have to remember to look - GitHub CLI authenticated with push access to
marcus/homebrew-tap - No
replacedirectives ingo.mod HOMEBREW_TAP_TOKENsecret present in the GitHub repo (CI tap job)
Beware of go.work: always use GOWORK=off when updating dependencies and
when validating install paths.
Local lint must match CI's golangci-lint v2.12.2, or trust CI:
gh run list --workflow=go-ci.yml --limit=1
Prepare (sidecar-specific)
1. Version
git tag -l 'v*' | sort -V | tail -1
SemVer: major / minor / patch as usual.
2. Sibling dependencies (td, tasks)
make sync-deps # pins every github.com/marcus/* requirement to its latest tag
check-release-state.sh enforces this and refuses to tag when one is behind.
go.work resolves those imports to the local checkouts, so drift is invisible
locally — both the gate and sync-deps use GOWORK=off. If a sibling jumped
several minors, decide deliberately (pin for a focused release vs take latest
and note it under Dependencies) and smoke its tab in the app.
3. CHANGELOG
## [Unreleased]
### Features
- …
### Bug Fixes
- …
### Dependencies
- …
Commit the changelog (and any dependency bump) on main, then push so
HEAD == origin/main. Leave the heading as ## [Unreleased] — make release
stamps it to ## [vX.Y.Z] - YYYY-MM-DD for you.
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 · 156 lines · 53 tokens per session scan A 0d658cba8d98
release-sidecar is a skill published in the GitHub repository marcus/sidecar (1,049 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 1,414 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 2026-08-30.
Other skills, from other repositories
pre-merge
The CI gate. Takes a feature branch from "eng says done" to "PR open against staging with green checks". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → open PR. Emits…
intake
The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes /intake. Owns the requirements interview — fleshes out thin ideas, proactively…
merge
The ship gate — the only skill that merges. --staging merges the feature→staging PR on green CI, deploys, verifies, emits a human test script and stamps the staging sign-off on approval. --production ships the double-confirmed release to main and deploys production. Never self-certifies staging; nothing reaches main…
msg
Root menu for msg skills, plus harness modes. --init is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo. Other modes: --init-staging (add a staging branch), --update…
lorekeeper-marketing
Marketing workflow for Lorekeeper — README copy, manifesto, positioning, and multi-agent A/B testing of copy variations. Load this when working on any user-facing content: README, docs/manifesto.md, positioning, comparison tables, or launch copy.
lorekeeper-reconcile
Reconcile and fact-check Lorekeeper memories against source materials, existing documentation, and internal consistency. Use when (1) the user provides reference materials to verify against, (2) the user requests a general knowledge audit, or (3) the user wants to verify specific topics. Updates memory scores and…