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 lantisprime/claude-sdlc --skill gate-signoffgit clone --depth 1 https://github.com/lantisprime/claude-sdlcWrote 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/lantisprime/claude-sdlc/gate-signoff)<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/gate-signoff"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/gate-signoff/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/lantisprime/claude-sdlc/gate-signoff"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/gate-signoff.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 | $0.00170 | $0.01649 |
| Opus 5 | $0.00085 | $0.00825 |
| Sonnet 5 | $0.00034 | $0.00330 |
| Haiku 4.5 | $0.00017 | $0.00165 |
Grade A, and why
gate-signoff 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 8d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gate Sign-off
Capture a fresh, auditable human approval at the end of a phase — without forcing a context-switch into the editor, but without letting approval degrade into a rubber-stamped "yes" either.
When this skill runs
- Invoked by phase commands —
/plan,/analyze,/design,/build,/test,/support— after the phase artifact has been written and shown to the human. - Does NOT run for
/deployor/fix-fast. Deploy has blast radius; fix-fast bundles three phases into one mini-gate. Both require the human to physically open and sign the gate file. - Does NOT run for
/docs. Docs is cross-cutting and has no dedicated gate file.
The sign-off dialogue
After the phase artifact is written, surface it and ask:
Phase artifact:
.claude/sdlc/<folder>/<task-slug>.md— please review.To sign off, paste the URL of the REQ / ticket / CR you're approving against. If no ticket system is configured (degraded mode), type
no ticketfollowed by the REQ ID(s) from the requirements artifact — e.g.no ticket REQ-12, REQ-13.
Wait for the user's raw input. Do not proceed on a bare "yes", "ok", "lgtm", or emoji — those are not acknowledgments, they're rubber stamps. If the response is one of those, re-ask with the prompt above.
Validation
Before writing the gate file, validate the input:
- URL form. If the input looks like a URL, confirm it parses (scheme + host + path).
- Host match. Read
config/tools.json→ticket_system.host. If present, warn (not block) when the URL's host differs — the human may be pointing at a secondary system on purpose. - Degraded form. If the input starts with
no ticket, require at least oneREQ-<n>token and confirm each REQ ID appears in the requirements artifact for this task. - Task-slug echo. The skill independently computes the expected gate path; the written file lands there. Do not let the user's pasted text redirect the output path.
If any check fails, explain the failure and re-ask once. After a second failure, pause and ask the human what to do — do not guess.
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.
- 8d ago First seen · 99 lines · 170 tokens per session scan A 20979e8f77ce
gate-signoff is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 170 tokens to every session and 1,649 once invoked, about $0.0009 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 skills, from other repositories
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
done-blocked
Reusable reporting contract for any agent that hands work back to the pipeline. Forces ONE of two terminal statuses (DONE or BLOCKED) with a specific evidence shape. Stops vague "probably finished" and "kind of stuck" verdicts.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
vertical-construction
Domain knowledge for the construction vertical (contractors, field crews) so architect and pm don't spec construction products naively. Covers the vocabulary (bid vs estimate, takeoff, retainage, change order, AIA G702/G703, lien waiver, draw schedule), the non-obvious money rules that incumbents like Procore price…
run-ticket
Run one exact Ticket through recovery, autonomous work, and its required landing, then write DONE or ESCALATED evidence back to that same Ticket. Use when a hosted trigger, agent runner, or person supplies a specific issue, tracker item, or file Ticket to work end to end. This skill does not select backlog work or…