Borrowing it
Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.agents/skills/midas-investigate/SKILL.mdgit clone --depth 1 https://github.com/okuzpe/midas-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/okuzpe/midas-harness/midas-investigate)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-investigate"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-investigate/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/okuzpe/midas-harness/midas-investigate"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-investigate.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 | $0.00066 | $0.01243 |
| Opus 5 | $0.00033 | $0.00622 |
| Sonnet 5 | $0.00013 | $0.00249 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
midas-investigate 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-investigate — root-cause before fix (non-advancing)
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). No stage precondition — runs anytime. Never mutatespaths.statestage/gates. Template:<paths.engine>/templates/investigate-record.md→{runs}/investigate/inv-NN.md. Playbook:<paths.engine>/templates/playbooks/debug-root-cause.md.
Standing debug investigation (gstack /investigate / Ley de Hierro): do not ship a speculative
fix until symptoms, flow, and a falsifiable root-cause hypothesis are frozen. Distinct from
/midas-explore (open-ended scoping outside the pipeline) and path-pass midas-qa (ad-hoc smoke, internal).
Does / Does not
| Does | Does not |
|---|---|
Freeze {runs}/investigate/inv-NN.md with symptoms → flow → hypothesis → evidence |
Advance stage or pass Phase-8 gates |
| Enforce Iron Law + 3 strikes before more blind fixes | Auto-apply production fixes without human OK on careful-class ops |
Point to regression proof (testing.md) once a fix is chosen |
Replace /midas-verify, /close-sprint, or /midas-tribunal |
Iron Law + 3 strikes
- Iron Law: no code fix for a defect until an investigation record exists for this failure (or the human explicitly waives with a one-line reason in progress notes).
- 3 strikes: after 3 failed fix attempts that do not deepen the investigation (new evidence
or revised hypothesis), stop — surface the blocker and the latest
inv-NN.md. Do not keep guessing. Matches Phase-7’s ~3 self-fix bound in7-sprint-execution.md/verification.md.
Args
| Arg | Meaning |
|---|---|
topic / symptom text |
What failed (error, test id, user report) |
--continue NN |
Amend existing inv-NN.md (new evidence / strike row) |
--dry-run |
Print draft in chat only — no write |
Procedure
1. Orient (scout)
Read paths.state. Resolve {runs}/. Dispatch scout for a tight pack:
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 · 102 lines · 66 tokens per session scan A 3583c18f312a
midas-investigate is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,243 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.