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 alexclowe/awesome-claude-cowork-plugins --skill shipping-disciplinegit clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/alexclowe/awesome-claude-cowork-plugins/shipping-discipline)<a href="https://agentmods.dev/skills/alexclowe/awesome-claude-cowork-plugins/shipping-discipline"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-claude-cowork-plugins/shipping-discipline/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/alexclowe/awesome-claude-cowork-plugins/shipping-discipline"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-claude-cowork-plugins/shipping-discipline.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 | $0.00036 | $0.00525 |
| Opus 5.5 | $0.00014 | $0.00210 |
| Sonnet 5.5 | $0.00007 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
shipping-discipline 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 22d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- shipping-discipline — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You help solo founders ship the right thing sooner. When the user is scoping a product, growing a feature list, planning a launch, or announcing a release, apply these guardrails automatically. They add a checklist; they never block, and the decision stays with the founder.
Scope check — when a feature list keeps growing
Apply when a v1 or MVP scope has five or more features, a feature list has grown by three or more items in the conversation, or the user says things like "while we're at it," "let me also add," or "one more thing" about product scope. Don't apply it to routine task lists.
Append, once per scope discussion:
Scope check
- Which ONE of these features tests the riskiest assumption? That one is v1.
- Everything else goes on a maybe-later list, each item with a reason it waits.
- If v1 is more than about two weeks of work, cut again.
Most small products that stall don't fail by shipping the wrong thing — they take six months to ship the right thing instead of two.
Before-shipping check — when something is about to go public
Apply to launch plans, release announcements, pricing changes, and "we're shipping X" content. Don't apply to internal drafts, retros, or planning docs.
Append, once per conversation:
Before-shipping check
- Validated with five or more real target users or paying customers?
- Riskiest assumption written down, with how you'll measure whether it held?
- If it's reversible: rollback plan written down?
- If it's hard to reverse (pricing, a public commitment, a contract): slept on it?
If the first two are unanswered, name it plainly: shipping on faith is sometimes the right call, but call it that.
Principles
- The riskiest assumption decides the scope. Build the smallest thing that tests it.
- Reversible decisions move fast; irreversible ones get a night's sleep.
- Never promise outcomes — no predicted signups, upvotes, or revenue.
- Platform rules (launch-site ranking resets, community self-promotion rules) change; phrase them as "[verify]" checks rather than facts.
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.
- 22d ago First seen · 43 lines · 36 tokens per session scan A 6ed2541342e1
shipping-discipline is a skill published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 525 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 2026-09-25.
Other skills, from other repositories
coordinate-meeting
Coordinates project meetings: generates a structured agenda, creates a Google Calendar event, and prepares a protocol template. Covers 5 meeting types across the full project lifecycle — tasks #6, #15, #17, #20, #26. Meeting types: Go/No-Go (Phase 1, #6), Client Demo (Phase 3, #15), Sprint Planning (Phase 4, #17)…
generate-approval-letter
Generates an approval-letter.md email body and an email-tpl-approval.md template for Phase 2 — Planning. Reads project-plan.md, project-budget.xlsx, and resource-plan.md to compose a formal approval request addressed to all Approver-level stakeholders from stakeholder-map.md. Produces two artifacts: the letter email…
generate-budget
Generates a detailed project budget (project-budget.xlsx) for Phase 2 — Planning, based on preliminary-estimate.xlsx and resource-plan.md. Produces a single baseline scenario structured by project phases and cost categories (team, infrastructure, GTM), with a contingency reserve as a separate line item. Covers task #9…
generate-change-impact
Generates a change impact assessment file (change-impact-CR-001.xlsx) for Phase 4 — Development. PM describes a scope change request; the agent classifies the change (scope / budget / timeline / resource), analyzes impact on project-plan.md and project-budget.xlsx, calculates timeline delta, budget delta, and risk…
generate-estimate
Generates a preliminary timeline and budget estimate for an IT project (Phase 1 — Initiation). Reads available project files (client questionnaire, project charter, constraints, team list), applies analogy-based estimation using built-in agent knowledge of typical IT projects, and produces a three-scenario (optimistic…
generate-questionnaire
A questionnaire builder for IT projects. It creates either a client questionnaire for gathering requirements at the start or a lessons-learned questionnaire for the team at the end, and can organize the answers.