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/ndisisnd/msg/pre-mergenpx skills add ndisisnd/msg --skill pre-mergegit clone --depth 1 https://github.com/ndisisnd/msgWrote 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/ndisisnd/msg/pre-merge)<a href="https://agentmods.dev/skills/ndisisnd/msg/pre-merge"><img src="https://agentmods.dev/badge/skills/ndisisnd/msg/pre-merge.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 | $0.00101 | $0.02422 |
| Opus 5 | $0.00051 | $0.01211 |
| Sonnet 5 | $0.00020 | $0.00484 |
| Haiku 4.5 | $0.00010 | $0.00242 |
Grade A, and why
pre-merge 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 3d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pre-merge
The CI gate. Runs after eng --build says a feature branch is done and takes it to
a PR open against staging with green checks. Pre-merge holds no human gate — the
human look at the running feature belongs to merge (../shared/refs/safety-floor.md
§ Human gates). Absorbs the retired /review and /test. Each run is independent.
Posture: release engineer — owns the gate; repeatable evidence over assertion, severity matched to reachability, tables over prose, JSON-first.
eng --build → /pre-merge → (fail → eng --build report=…, repeat) → PR feature→staging → merge --staging
Usage
/pre-merge— gate the current feature branch againststaging/pre-merge --init— the one-time setup: detect tooling → interview → gated install/scaffold → writedevkit/policy.json; no gate run (refs/protocol-init.md). The.github/workflows/CI pipeline is part of the detect unlesspolicies.github_actions.enabledisfalse— a settled opt-out, not a gap/pre-merge --update— reconcile the manifest with codebase reality: re-run preflight → diffcomponents[]→ approve the delta → applypresent/active_when/new-component changes only, never re-grading user-set criticality or re-prompting settled opt-outs (refs/protocol-init.md)/pre-merge --update-criticality— the criticality reconcile: inventory untagged tests → evidence-cited proposals → one human gate → markers committed +criticality_reviewrestamped (refs/protocol-update-criticality.md)/pre-merge --prd <path>(repeatable) — name the PRD explicitly. Theprdgroup (prd-consistency,manual-test-plan) runs by default whenever afeatures/prd-<N>-*/PRD matches the branch; this flag overrides an ambiguous or missing match/pre-merge --prior-issues <path>/--full-secret-scan— load a prior verdict JSON to mark regressions / make thesecuritycomponent scan the full tree (default: diff-only)/pre-merge --flaky <N>/--changed-only— retry failing e2e / unit-int tests up toNtimes; skip platform components whose surface the diff doesn't touch (refs/_common.md).--minified/--full— force test selection on for this run (a trial; nothing written) / force the full suites, the kill switch. Flag beats policy:--full>--minified>policies.test_selection(refs/executor.md§3c)/pre-merge --quiet/--status <n>m— suppress or retune this run's status heartbeat; flag beats policy beats default, floor 2 minutes (../shared/refs/status-heartbeat.md)
What ships with it
38 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.
- refs/_common.md 5.1 KB
- refs/executor.md 43 KB
- refs/finding-schema.md 3.1 KB
- refs/output-schema.md 8.5 KB
- refs/platform-profiles.md 3.2 KB
- refs/platform/protocol-a11y.md 4.6 KB
- refs/platform/protocol-api.md 3.9 KB
- refs/platform/protocol-e2e.md 1.4 KB
- refs/platform/protocol-load.md 3.9 KB
- refs/platform/protocol-migration.md 4.7 KB
- refs/platform/protocol-mobile.md 5.2 KB
- refs/platform/protocol-perf.md 4.0 KB
- refs/platform/protocol-smoke.md 5.9 KB
- refs/prd/protocol-manual-test-plan.md 7.2 KB
- refs/prd/protocol-prd-consistency.md 8.0 KB
- refs/protocol-init.md 34 KB
- refs/protocol-update-criticality.md 9.0 KB
- refs/refusal-patterns.md 5.1 KB
- refs/severity-rubric.md 6.4 KB
- refs/stubs/.prettierrc.json 90 B
- refs/stubs/.size-limit.json 52 B
- refs/stubs/biome.json 192 B
- refs/stubs/docker-compose.test.yml 1.6 KB
- refs/stubs/eslint.config.js 362 B runs code
- refs/stubs/playwright.config.ts 427 B runs code
- refs/stubs/pre-merge.yml 1.3 KB
- refs/stubs/README.md 2.4 KB
- refs/stubs/ruff.toml 184 B
- refs/stubs/seed-test.ts 2.0 KB runs code
- refs/stubs/vitest.config.ts 336 B runs code
- refs/sync.md 3.0 KB
- refs/universal/protocol-coverage.md 5.8 KB
- refs/universal/protocol-integration.md 3.2 KB
- refs/universal/protocol-mechanical.md 3.7 KB
- refs/universal/protocol-regression.md 5.1 KB
- refs/universal/protocol-security.md 4.5 KB
- refs/universal/protocol-unit.md 2.8 KB
- scripts/script-resolve-diff.sh 2.9 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.
- 3d ago First seen · 101 lines · 101 tokens per session scan A b3d440bdaea3
pre-merge is a skill published in the GitHub repository ndisisnd/msg (6 stars, last pushed 17d ago), licensed MIT. It adds 101 tokens to every session and 2,422 once invoked, about $0.0005 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
skillspec-migrate
Complete a .agent.partial file by resolving TODO markers.
skill-writer
Review a SkillSpec .agent file for quality, correctness, and adherence to SkillSpec design principles.
skillspec-backport
Reconcile changes from a modified SKILL.md back into the .agent source file.
skillspec-test
Execute test blocks from a SkillSpec .agent file.
pre-push
Runs the local equivalent of the CI merge gate before you push. Detects which areas (Python, TypeScript, docs) your changes touch, auto-fixes what it can, then runs only those checks. Use when the user asks to run pre-push checks, get push-ready, verify changes before pushing or opening a PR, "make sure CI will pass"…
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…