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 tjdrhs90/rn-launch-harness --skill rn-harness-retrogit clone --depth 1 https://github.com/tjdrhs90/rn-launch-harnessWrote 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/tjdrhs90/rn-launch-harness/rn-harness-retro)<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-retro"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-retro/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/tjdrhs90/rn-launch-harness/rn-harness-retro"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 71 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 73 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 74 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 75 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00000 | $0.02661 |
| Opus 5 | $0.00000 | $0.01331 |
| Sonnet 5 | $0.00000 | $0.00532 |
| Haiku 4.5 | $0.00000 | $0.00266 |
Grade A, and why
rn-harness-retro 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 12d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rn-harness-retro — Harness Retrospective
Retrospective analysis of a project built with the RN Launch Harness pipeline. Evaluates the app against Anthropic's harness design principles and optionally verifies the app runs correctly.
"Every component in a harness encodes an assumption about what the model can't do on its own, and those assumptions are worth stress testing." — Anthropic
Trigger
- User invokes
/rn-harness-retro - Called after the full pipeline completes (post Phase 10: Submit)
Arguments
Parse $ARGUMENTS for:
[project-dir]— Target project path. If omitted, locate the graduated project — runs graduate at Phase 5 into a top-level<app-slug>/folder, sodocs/harness/is NOT at the run-directory root:
One match →# from the run-directory root: find completed pipelines find . -maxdepth 4 -path './*/docs/harness/state.md' 2>/dev/nullcdinto that<app-slug>/. Multiple → listrun_id/statusand ask which. Only fall back to current directory if you are already inside the project folder (./docs/harness/state.mdexists).--run-app— Attempt to build and run the app, verify it works on simulator--deep— Deep analysis including source code review
Phase 1: Collect Harness Outputs
1.1 Read All Harness Artifacts
Read every file in docs/harness/ and docs/specs/:
docs/harness/state.md → Pipeline state
docs/harness/config.md → Configuration
docs/harness/contract.md → Contract (Generator-Evaluator agreement)
docs/harness/build-log.md → Build log (rounds, scores)
docs/harness/pipeline-log.md → Pipeline event log
docs/harness/plans/ → PRD and planning documents
docs/harness/feedback/ → QA feedback (all rounds)
docs/harness/handoff/ → Handoff documents (all rounds)
docs/harness/screenshots/ → Screenshots taken during evaluation
docs/specs/ → Spec files and progress dashboard
Read all files and reconstruct the full pipeline history.
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.
- 12d ago First seen · 298 lines · 0 tokens per session scan A 9cb93d627152
rn-harness-retro is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,661 tokens. 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
appstore-publish
A workflow guide for publishing an app to the App Store, including prerequisites, tool loading, submission, and resubmission steps.
mimi-seed-update
An update guide for Mimi Seed that identifies the installed version and installation type, then applies the matching update process. It also covers plugin installation.
playstore-publish
A guide for publishing to Google Play, including required conditions, tool loading, the run sequence, in-app products, and subscriptions. Google Play is Google’s store for Android apps and digital purchases.
mimi-seed
A guide for using Mimi Seed, including required conditions, loading its tools, the execution flow, and linking local login details to a remote MCP service. MCP is a way for an agent to use tools provided by another program or service.
video-create-publish
Create, render, validate, and optionally publish polished short-form videos and YouTube Shorts with Mimi Seed. Use for story-to-video production, vertical social videos, carousel-to-video adaptations, visual-quality revisions, or YouTube upload/status work where typography, shorts-style burned captions, human-safe…
deploy
A Mimi Seed release workflow that connects CI builds, release-readiness checks, release-note creation, and store updates. CI is automated software that builds and checks code; the stores are Google Play and Apple’s App Store.