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 manishiitg/coding-agent-loop --skill release-candidate-to-reviewed-gategit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/release-candidate-to-reviewed-gate)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/release-candidate-to-reviewed-gate"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/release-candidate-to-reviewed-gate/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/manishiitg/coding-agent-loop/release-candidate-to-reviewed-gate"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/release-candidate-to-reviewed-gate.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 | $0.00026 | $0.00703 |
| Opus 5.5 | $0.00010 | $0.00281 |
| Sonnet 5.5 | $0.00005 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
release-candidate-to-reviewed-gate 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 20d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Candidate to Reviewed Gate
Outcome
Produce an attempt-level journey result and a reviewed release gate proposal for the exact SHA, build, and environment. A proposed pass, owner approval, provider-published status, merge, and deployment are distinct states.
When to use
Use when a small team needs a repeatable release quality decision from browser and CI evidence. For a single QA chat question, one Crew may be enough. Add the Flaky Test Investigator only for an intermittent result requiring its own evidence and owner.
Discovery and user direction
Inspect existing QA Crews, candidate identity, policy revision, required suites, attempts, evidence retention, owners, and status destination. Propose reuse or reviewed creation. Show the exact route before Builder applies it; selection leaves setup pending.
Required inputs
Bind release or PR ID, SHA, immutable build artifact, environment, cutoff, approved journey revision, required suite policy, test account scope, gate owner, and status authority.
Plan and AgentWorks tools
Reuse Browser Journey QA Analyst and Release Quality Assistant. Journey writes journey-result/v1; run the bundled validator before Gate consumes it. If attempts conflict, route a bounded artifact to Flaky Test Investigator, validate its flake-investigation/v1, and keep original failures visible. Gate re-reads all required suite records and writes release-quality-brief/v1. Insert explicit validator steps in the Workflow. Publish only the exact owner-approved decision through a separately authorized route.
Knowledge and persistence
Save release, SHA, build, environment, policy, journey, suite, attempt, source, reviewer, approval, provider receipt, and run IDs. A new SHA or build is a new gate decision. Reruns preserve prior attempts and waivers.
Validation and reporting
The validator checks identity, required suite coverage, evidence, flake disposition, verdict, and publication receipt. Fictional journey and gate pass; the wrong-build pass fails. The flake investigation pairs with a needs-review gate; owner approval and status receipt are later artifacts. The reporting dashboard shows tested candidate, required suites, failures, blocked and stale evidence, owner decision, published state, and cost separately.
What ships with it
12 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.
- examples/approved-release-quality-brief.json 1.2 KB
- examples/flake-investigation.json 737 B
- examples/flake-needs-review-gate.json 1.4 KB
- examples/invalid-release-quality-brief.json 1.2 KB
- examples/journey-result.json 534 B
- examples/release-quality-brief.json 1.2 KB
- examples/status-publication.json 350 B
- playbook.json 4.9 KB
- references/team-and-handoffs.md 3.4 KB
- scripts/test_validate_handoff.py 3.5 KB runs code
- scripts/validate_handoff.py 8.9 KB runs code
- SETUP.json 2.9 KB
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.
- 20d ago First seen · 48 lines · 26 tokens per session scan A 8563fa393d6a
release-candidate-to-reviewed-gate is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 26 tokens to every session and 703 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 2026-09-27.
Other skills, from other repositories
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
rn-testing
This skill should be used when the user asks to "write a Maestro test", "create E2E flows", "add testIDs", "run UI tests", "run E2E tests", "verify a feature works", "test my screen", "set up maestro-runner", "mock network requests", "inspect store state", "write test assertions", or needs guidance on test timing…
capturing-proof
This skill should be used when the user asks to "capture proof", "record a demo of this feature", "make a video showing it works", "record the flow for the PR", "generate a PR body", "capture screenshots for the PR", "proof-capture", or when a verified feature needs PR-ready proof artifacts (video + numbered…
run-action
Explicit Codex workflow: Execute a learned Maestro flow ("action") by name with optional -e KEY=VALUE parameters. Looks the flow up via packages/rn-dev-agent-core/dist/learned-actions.js (same inventory as $rn-dev-agent:list-learned-actions), then replays it via cdprunaction — auto-repair-aware orchestration with…
build-and-test
Explicit Codex workflow: Build the Expo/React Native app (local or EAS), install it, start Metro, then test a requested feature end-to-end.
tapp
Use Tapp to see, drive, explore, and verify real application surfaces on iOS simulators, Android emulators/devices, or the web. Use when a user asks an agent to test an app or UI change, find bugs, inspect or screenshot a screen, exercise a journey, create a replayable flow, gather release evidence, run the…