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 juan294/cc-rpi --skill rpi-remediategit clone --depth 1 https://github.com/juan294/cc-rpiWrote 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/juan294/cc-rpi/rpi-remediate)<a href="https://agentmods.dev/skills/juan294/cc-rpi/rpi-remediate"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/rpi-remediate/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/juan294/cc-rpi/rpi-remediate"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/rpi-remediate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Tool Misuse · line 266 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00030 | $0.04120 |
| Opus 5 | $0.00015 | $0.02060 |
| Sonnet 5 | $0.00006 | $0.00824 |
| Haiku 4.5 | $0.00003 | $0.00412 |
Grade A, and why
rpi-remediate 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 6d 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The request is supplied as literal arguments: $ARGUMENTS
Remediate Pre-Launch Findings
Resolve every confirmed actionable finding within the authorized remediation scope. Record every finding locally, group related causes and ownership, complete TDD repairs and independent review, integrate sequentially per wave, and verify locally. Keep narrow work with the parent; delegate only useful independent work. External issue publication requires authorization; local records preserve the same evidence and dispositions.
Input
If the request specifies report paths, use it as the report path or wave selector
(e.g., wave=2 to resume at Wave 2). Otherwise, auto-detect the report
at docs/agents/pre-launch-report.md. If no report exists, suggest
running rpi-pre-launch first and STOP.
If wave=N is provided, load the prior approved plan/handoff and verify its
state before resuming Wave N. Apply the durable handoff
contract and revalidate actual worktree/base/current state and candidate/check
identity. A selector alone is not evidence of prior approval.
When a parent uses a machine-readable assignment/acceptance record, follow the dispatch contract and validate it before claiming complete coverage. The record is optional for a small parent-only task; required review, TDD and phase acceptance still apply.
Step 1: Parse & Plan
Gather context before making any changes.
-
Read the pre-launch report completely. Resolve the bundled finding validator relative to this skill; never assume a Claude-only project script path.
The report uses a 16-section format. Findings live in sections 4-11 (Frontend, Backend, Performance, DevOps/SRE, Security, Architecture, QA, UX), plus §11a (Agent-Facing Surface) when that domain applies. Domain coverage is independent of how many investigators supplied it; a failed or absent investigator does not make a required domain inapplicable. Section 14 (Before/After/Later) is the wave-ordering index. Section 15 (Open Questions) is not findings; preserve its unresolved decisions separately.
What ships with it
4 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.
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.
- 6d ago First seen · 379 lines · 30 tokens per session scan A ad7933edec26
rpi-remediate is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 4,120 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
kotlin-testing
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…