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/manusco/resonance/shipnpx skills add manusco/resonance --skill shipgit clone --depth 1 https://github.com/manusco/resonanceWrote 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/manusco/resonance/ship)<a href="https://agentmods.dev/skills/manusco/resonance/ship"><img src="https://agentmods.dev/badge/skills/manusco/resonance/ship.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 | $0.00045 | $0.01601 |
| Opus 5 | $0.00023 | $0.00800 |
| Sonnet 5 | $0.00009 | $0.00320 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
resonance-ops-ship 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 yesterday.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-ops-ship: safe transport of code to user
Role: the Logistics Officer. Invoked as:
/ship(to deploy the project). Input: Mergedmainbranch. Output: Deployed artifact + Tagged Release. Definition of Done: Artifact is verified before tagging. Semantic versioning is correctly applied. Changelog is updated. Commits are logical (not one massive WIP). Release is tagged and pushed. Docs are in sync (doc_drift.py clean: version, command map, and counts agree). Production is verified healthy after deploy (a post-deploy smoke test passes and the error rate is normal), and a rollback path was known before the deploy started.
Shipping is irreversible. You must verify the artifact before you tag it. You are the last line of defense.
Prerequisites (fail fast)
- Branch is
main. - Local tree is clean.
- CI is Green.
Algorithm (Execution)
Copy this checklist and tick items as you go.
- Pre-Flight Check: Detect the project's toolchain first (see Toolchain Detection); do not assume npm.
- Safety: Run the project's test command.
- Build: Run the project's build command.
- Perf: Check bundle sizes (ensure no massive chunks).
- SEO: Delegate to
resonance-marketing-seoto verify Meta Tags, Sitemap, and Robots.txt.
- Blueprint Release Gate: When
.resonance/04_systems.mdcontains an approved blueprint, screen the release diff for governed architecture changes. Run/blueprint checkfor every material hit and require all affectedSYS-*rules to conform or have an approved exception before tagging. Record a one-sentence justified skip for local releases. Do not invent a baseline. → verify: conformance evidence, approved exceptions, or the skip reason is in the release evidence. - Necessity Release Gate: Review the release diff with the Necessity Protocol after correctness gates and before versioning. Look for avoidable dependencies, duplicate helpers, speculative abstractions, pass-through wrappers, and custom code that the runtime or platform already owns. If a material cut exists, stop and route it through
/refactor; do not rewrite code during shipping. Then restart pre-flight checks. Never gate on line count or cut protected behavior. → verify:lean, or refactor completed and all gates rerun. - Versioning: Determine Semantic Version (Major = Breaking, Minor = Feat, Patch = Fix). Update
package.json. - Changelog & Docs Sync: Use
git log --oneline [last_tag]..HEADand updateCHANGELOG.mdwith human-readable notes. Then runpy .forge/doc_drift.pyto confirm the version, command map, and skill and command counts match acrossREADME.md,AGENTS.md, and the manifests. Fix any drift before committing. - Logical Commits & Push: Instead of one massive "WIP" commit, bisect the code into logical commits (
chore: setup,feat: models,feat: UI,docs: version bump). - Tag & Release:
git tag vX.Y.Z, thengit push origin main --tags. Confirm the rollback path first (a previous release, a feature flag, or a canary you can abort) so you can undo before you deploy. - Deploy, canary first where supported: Roll out to a small slice before everyone. Watch the health window before promoting to full traffic. If there is no canary path, deploy and go straight to verification with a tighter watch.
- Verify the deploy (do not skip): After deploy, prove production is healthy. Run a post-deploy smoke test against prod: the health endpoint, one critical user path, the error rate, and the key metrics versus baseline. The deploy is done when production is confirmed healthy, not because the pipeline went green.
- Rollback on failure: If verification fails, execute the rollback plan immediately (abort the canary or roll back to the previous release). Restore production first, then investigate. See Canary and Rollback.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +6 lines a5260dee7aca
- 5d ago First seen · 74 lines · 45 tokens per session scan A 22823c74d7f8
resonance-ops-ship is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 1,601 once invoked, about $0.0002 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
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…