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 skills add SenMuShare/senmu-buildos --skill senmu-build-deliverygit clone --depth 1 https://github.com/SenMuShare/senmu-buildosWrote 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/senmushare/senmu-buildos/senmu-build-delivery)<a href="https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-delivery"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-delivery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-delivery"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-delivery.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.00586 |
| Opus 5.5 | $0.00014 | $0.00234 |
| Sonnet 5.5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
senmu-build-delivery 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 29d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery Management
Match authorized Git/release actions to production and rollback facts. Routine commits do not activate.
Route by Outcome
- Batches, worktrees, merges, hotfixes: Code/Merges.
- Cross-session or parallel work: Change Units.
- Resumable review coverage: Review Execution.
- Topology, projections, release units: Repositories.
- Work/version logs, handoffs: Logs.
- Versions, tags, artifacts: Artifacts.
- Authority, production, rollback: Authorization.
- Deployment, secrets, post-release: Security. Before public exposure: Public-service baseline.
Read-only advice never merges, tags or deploys. Release entrypoints must be executable. Assurance handles explicit audits, disputes or required independent verdicts, not routine checks.
Core Contract
- Recover authority, lines, batch, release unit and recovery from owners/Git. Ask only about consequential ambiguity.
- Reuse
in_progressfor shared version/acceptance/release/rollback. Isolate real parallel work. Never edit an integration line or reopen sealed work. Unrelated tasks cannot chain from another task branch; inseparable dependencies may use registered sealed-parent stacks with explicit baselines and integration order under Change Units. - Changing agents/sessions preserves the Change Unit.
manage_change_unit.py inspectlocates its registered state; resume within existing write authority. - One item does not finish a batch.
reviewfreezes a commit without sealing; repair open batches in place. Seal completed scope only after checks and required review/repairs. Releases require release authority. - Declare
mainasintegrationorrelease_ready; stack only on sealed parents. - Keep one release source; verify identity before tags/artifacts. Reuse valid source evidence; check artifacts/environments separately.
- Distinguish candidate, build, deployment, production verification and version. Tag established facts; preserve rollback.
- No release intent means no release; “do not release yet” persists. Product owns behavior changes. New commits renew candidate conclusions through changed/affected scope, not repeated full review or renewed unchanged authority.
What ships with it
32 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.
- agents/openai.yaml 288 B
- assets/delivery-governance/ARTIFACT_MANIFEST.template.json 782 B
- assets/delivery-governance/BRANCHING.template.md 9.0 KB
- assets/delivery-governance/CHANGE_REVIEW_CONTROL.template.json 662 B
- assets/delivery-governance/CHANGELOG_RULES.template.md 576 B
- assets/delivery-governance/CHANGELOG.template.md 88 B
- assets/delivery-governance/CLEANUP_RELEASE_ASSETS.template.sh 13 KB runs code
- assets/delivery-governance/DEPLOYMENT.template.md 4.2 KB
- assets/delivery-governance/PUBLICATION.template.md 1.7 KB
- assets/delivery-governance/RELEASE_CONTROL.template.json 1.6 KB
- assets/delivery-governance/RELEASE_RECORD.template.md 2.7 KB
- assets/delivery-governance/RELEASE_RETENTION.template.env 1.4 KB
- assets/delivery-governance/REPOSITORY_AND_RELEASE_UNITS.template.md 965 B
- assets/delivery-governance/TEST_RELEASE_RETENTION.template.sh 4.3 KB runs code
- assets/delivery-governance/VERSION_AND_RELEASE.template.md 13 KB
- assets/delivery-governance/VERSION.template 6 B
- assets/delivery-governance/WORKLOG_ENTRY.template.md 1.8 KB
- references/code-management-and-integration.md 18 KB
- references/collaboration-and-version-logs.md 9.5 KB
- references/deployment-testing-and-security.md 6.2 KB
- references/multi-agent-change-units-and-version-line-closeout.md 14 KB
- references/release-authorization-and-production-truth.md 11 KB
- references/repository-boundaries-and-release-units.md 13 KB
- references/security/public-service-security-baseline.md 5.0 KB
- references/version-artifacts-and-release.md 12 KB
- scripts/export_public_projection.py 8.0 KB runs code
- scripts/git_review_inventory.py 8.1 KB runs code
- scripts/inspect_git_workspace.py 16 KB runs code
- scripts/manage_change_unit.py 42 KB runs code
- scripts/validate_change_review.py 30 KB runs code
- scripts/validate_release_control.py 15 KB runs code
- scripts/verify_release_identity.py 2.6 KB runs code
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.
- 29d ago Changed · +1 lines 6a92c2c65c65
- 1mo ago Changed f836fa054eb2
- 1mo ago Changed 3b1efdaaa9db
- 1mo ago Changed · -2 lines · -10 tokens per session d77164ad02a2
- 1mo ago First seen · 36 lines · 45 tokens per session scan A e041782ca8f2
senmu-build-delivery is a skill published in the GitHub repository SenMuShare/senmu-buildos (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 35 tokens to every session and 586 once invoked, about $0.0001 per session on Opus 5.5. 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
github-project-management
GitHub project management with issue tracking, project-board automation, and sprint planning. Use when triaging or organizing issues, automating a project board, planning a sprint, or running release/roadmap coordination on GitHub.
pace-release
A release-management workflow for coordinating software versions from preparation through deployment and closure. A release is a planned delivery of changes to users or an environment.
hotfix
Emergency fix workflow that bypasses normal sprint processes with a full audit trail. Creates hotfix branch, tracks approvals, and ensures the fix is backported correctly.
openproject-codex
Use the OpenProject Codex plugin to inspect and manage work in Codex through the OpenProject API.
project-management-jira-workflow-steward
You are a Jira Workflow Steward, the delivery disciplinarian who refuses anonymous code. If a change cannot be traced from Jira to branch to commit to pull request to release, you treat the wor...
Jira Workflow Steward
Expert delivery operations specialist who enforces Jira-linked Git workflows, traceable commits, structured pull requests, and release-safe branch strategy across software teams.