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 rijuvashisht/Magneto --skill investigategit clone --depth 1 https://github.com/rijuvashisht/MagnetoWrote 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/rijuvashisht/magneto/investigate)<a href="https://agentmods.dev/skills/rijuvashisht/magneto/investigate"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/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/rijuvashisht/magneto/investigate"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/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 | $0.00000 | $0.00537 |
| Opus 5 | $0.00000 | $0.00269 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/investigate — Root-Cause Debugging with Auto-Freeze
Role: Debugger
Inputs: bug description or error trace
Outputs: review-report.md with root-cause analysis
Audit actions: investigate.started, investigate.hypothesis_tested, investigate.resolved
Why This Skill Exists
Karpathy's Iron Law: No fixes without investigation. AI assistants fix symptoms. /investigate forces root-cause analysis before any change.
The Protocol
Step 1: Auto-freeze to the affected module
From the error trace or bug description, identify the primary file. Then:
magneto freeze <module-path>
This prevents drive-by fixes in unrelated code while debugging.
Step 2: Gather evidence (don't theorize yet)
magneto graph neighbors <failing-node> # who calls this?
magneto query --search "<error-keyword>" # has this happened before?
magneto memory show --tags bugs,debugging # similar past bugs
Step 3: Generate 3 hypotheses
Write them down explicitly. Example:
- Race condition in token refresh (evidence: timestamps cluster during concurrent requests)
- Stale cache (evidence: fresh deploys always work)
- Upstream API changed schema (evidence: nothing local changed)
Step 4: Test each hypothesis with minimal code
For each:
- Define the verification step
- Execute it (add logging, run a test, inspect state)
- Mark as confirmed, ruled-out, or inconclusive
Emit audit: magneto audit add investigate.hypothesis_tested --payload '{"hypothesis":"...","result":"..."}'
Step 5: STOP after 3 failed fix attempts
If 3 attempts to fix haven't resolved it, STOP and:
- Write findings to review-report.md
- Ask the user for more info
- DO NOT keep trying variations — that's how bugs get hidden
Step 6: Apply the fix
Only after root cause is confirmed:
- Apply the minimal fix (Karpathy Rule 2: simplicity first)
- Add a regression test
- Run
magneto unfreeze
Trigger Phrases
- "investigate"
- "debug this"
- "root cause"
- "what's wrong with"
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 · 77 lines · 0 tokens per session scan A e4097c8491aa
investigate is a skill published in the GitHub repository rijuvashisht/Magneto (6 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 537 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
langbot-plugin-dev
Develop, debug, and test LangBot plugins. Use when creating new LangBot plugins, fixing plugin bugs, setting up a LangBot test environment, or testing plugins via WebSocket. Covers plugin component architecture (EventListener, Command, Tool), the plugin SDK API (invokellm, getllmmodels, sendmessage, plugin storage)…
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
node-connect
Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale…
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.
ax-cpp-agent-observability
Use when writing C++ code with axllm for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.
ax-go-agent-observability
Use when writing Go code with github.com/ax-llm/ax/packages/go for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.