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 Kyne0328/rel-ai-local-coding-agent --skill rel-ai-investigationgit clone --depth 1 https://github.com/Kyne0328/rel-ai-local-coding-agentWrote 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/kyne0328/rel-ai-local-coding-agent/rel-ai-investigation)<a href="https://agentmods.dev/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-investigation"><img src="https://agentmods.dev/badge/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-investigation/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/kyne0328/rel-ai-local-coding-agent/rel-ai-investigation"><img src="https://agentmods.dev/badge/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-investigation.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 | $0.00059 | $0.00354 |
| Opus 5 | $0.00030 | $0.00177 |
| Sonnet 5 | $0.00012 | $0.00071 |
| Haiku 4.5 | $0.00006 | $0.00035 |
Grade A, and why
rel-ai-investigation 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 11d 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.
What it actually says
Rel.AI Investigation
Reuse the active work_id opened by rel-ai-workflow. Do not call relai_work with action: "begin" when the same objective already has a work session.
Use runtime workflow guidance after every Rel.AI call to decide whether another search, read, measurement, or broader boundary is actually useful. workflow.recommendedActions is the default calibration; current evidence and the investigation question determine when proof is sufficient.
- State the question and define what would count as sufficient proof before gathering more context.
- Escalate evidence in this order:
bootstrap -> search/inspect -> targeted reads -> bounded measurement -> broader reads only if required. - Prefer symbol, reference, caller, search, runtime, or package evidence over broad file dumps. Reuse evidence that is still current.
- Read only the files and ranges needed to verify the claim. Use bounded one-shot commands for reproducible measurements; never start a managed process for an audit command.
- Stop when the required proof exists. More available context is not a reason to continue investigating.
- Classify conclusions as observed, verified, inferred, or unresolved. Tie inferences to the evidence that supports them.
- This skill does not edit. If implementation is also requested, hand the verified findings to
rel-ai-workfloworrel-ai-debugginginstead of restarting the investigation.
What ships with it
1 file 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.
- 11d ago First seen · 18 lines · 59 tokens per session scan A 971ad5a9a3b6
rel-ai-investigation is a skill published in the GitHub repository Kyne0328/rel-ai-local-coding-agent (19 stars, last pushed 6d ago), licensed Apache-2.0. It adds 59 tokens to every session and 354 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
codexless-browser-repair
Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…
fix-default
A default procedure for handling bug fixes, organised as a three-step scan and a CP process. The input does not explain what the three steps or CP process contain.
repair-prevention-assessment
A completion gate for fixes and self-repair work. It creates a machine-checkable assessment that separates evidence a current issue is closed from evidence that the fix will remain effective.
diagnosing-bugs
Diagnose bugs with a reproducible red signal, minimized case, ranked hypotheses, and regression test.
conspiracy
Investigate every bug as if it were intentional. Ask who benefits, connect dots from git history and naming, then arrive at the correct technical fix anyway. Use when user types /conspiracy, says "activate conspiracy" or "conspiracy mode".
senior-at-3am
Maximum terse incident-response persona. No pleasantries, no explanation unless asked. Format - what is broken, one-line fix, done. Mild irritation acceptable, never rude. Use when user types /senior-at-3am, says "activate senior-at-3am" or "3am mode".