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 synaptiai/synapti-marketplace --skill pr-lifecyclegit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/pr-lifecycle)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/pr-lifecycle"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/pr-lifecycle/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/synaptiai/synapti-marketplace/pr-lifecycle"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/pr-lifecycle.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 | $0.00076 | $0.01099 |
| Opus 5.5 | $0.00030 | $0.00440 |
| Sonnet 5.5 | $0.00015 | $0.00220 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
pr-lifecycle 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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Lifecycle
Policy reference for PR creation and the pre-merge finding-ledger gate; the runnable bash lives in commands/pr.md and commands/merge.md.
Contract
Iron law: no PR without verification — a PR body that cannot show test, lint, and runtime evidence is not ready. Consumed by /flow:pr (Phase 1 pre-flight; Phase 4 verification gate, body assembly, push, create, reviewer suggestion at step 11) and by /flow:merge Phase 1 (finding-ledger check). Returns the policy those commands apply: four pre-flight conditions, five verification-gate conditions, the PR body section order, the reviewer cascade, and the two ledger rules that block a merge. Permitted skips: none — pre-flight conditions 1, 2, and 4 are hard errors; condition 3 is a warning that offers /flow:commit.
Pre-Flight Gate (/flow:pr Phase 1)
| # | Condition | On failure |
|---|---|---|
| 1 | Not on the default branch | Hard error — PRs come from feature branches |
| 2 | At least one commit ahead of the default branch | Hard error — empty PRs are noise |
| 3 | No uncommitted changes | Warning — offer /flow:commit first |
| 4 | No existing open PR for this branch | Hard error — update the existing PR |
Verification Gate (/flow:pr Phase 4)
All five must hold before creation; otherwise stop:
- All quality commands (lint, test, typecheck) pass — output captured for the PR body.
- Self-review completed against the
code-quality-principleschecklist. - Change classification shows no out-of-context files.
- Every acceptance criterion has a "Met" or "Interpreted" status with concrete evidence.
- No P1 findings remain from code review.
"Get the PR up and fix it after", "the reviewer will catch it", "small change", and "CI will validate it" are not exemptions. The eight quality gates flow enforces are mapped in gate-configuration.md.
PR Body
Generated from templates/pr-body.md plus review findings and the decision journal. Section order: Summary (2–3 sentences), Closes, Changes (grouped by area), Comprehension Report, Key Decisions (public journal entries; internal entries redacted), Requirements Adherence (criterion → status → file:line evidence), Review Findings (P1/P2/P3), Known cosmetic notes, Review Cycle History, Verification checklist, Verification Verdict, Files Changed. Reviewers skim Summary, Requirements Adherence, Verification in under thirty seconds.
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.
- 1mo ago Changed · -65 lines · +3 tokens per session 640ec859c28e
- 1mo ago First seen · 127 lines · 73 tokens per session scan A 46d536051739
pr-lifecycle is a skill published in the GitHub repository synaptiai/synapti-marketplace (7 stars, last pushed 12d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,099 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
create-pr
User-triggered Enterprise PR recorder for a completed phase. Stacked plans publish their phase branch through the publish-phase repair command; other plans create or reuse the current-branch PR. Links the tracked issue and records PR identity. It never posts review verdicts, never rebases, and never force-pushes.
up-to-date
Preflight sync and situational brief before repo work: fetches origin, reports ahead/behind divergence (with a no-upstream/detached-HEAD fallback), recent commits, open PRs and issues touching the work, and dirty-tree warnings, then names one recommended first action. Read-only by default — never pulls, rebases…
create-pr
Creates a GitHub Pull Request on the current branch with a description focused on WHAT changed (not HOW). Uses emojis in the title and description. Use when the user asks to create a PR, open a pull request, or submit changes for review. Triggers on mentions of PR, pull request, merge request, or code review.
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
git-workflow
Manages branches, worktrees, atomic commits, and branch completion by merge, PR, preserve, or discard. Use when starting feature work that needs a branch or an isolated workspace, making commits during development, or finishing a development branch. Also use when the user says "set up worktree", "create PR", "finish…