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 bjornjee/agent-dashboard --skill investigategit clone --depth 1 https://github.com/bjornjee/agent-dashboardWrote 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/bjornjee/agent-dashboard/investigate)<a href="https://agentmods.dev/skills/bjornjee/agent-dashboard/investigate"><img src="https://agentmods.dev/badge/skills/bjornjee/agent-dashboard/investigate.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00625 |
| Opus 5 | $0.00010 | $0.00313 |
| Sonnet 5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate a codebase question or concern. This is a read-only skill — do not modify any files.
Question or concern: $ARGUMENTS
Instructions
Follow these phases in order.
Phase 0: Sync
- Switch to main:
git checkout main - Pull latest:
git pull origin main
Phase 1: Scope
- Parse the question or concern — is it about behavior, architecture, performance, a failure, a dependency, or something else?
- If the scope is ambiguous, ask the user to clarify before proceeding.
- Identify the likely entry points in the codebase (files, modules, services).
Gate: The investigation scope is clear and bounded.
Phase 2: Research
- Trace code paths — read the relevant source files, following the call chain from entry point to the area of interest.
- Read tests — understand what is tested and what is not. Look for edge cases and assumptions.
- Check git history — use
git log --all -S "<term>"to find when relevant code was introduced or changed. Usegit blamefor context on specific lines. - Check dependencies — if the question involves a library or framework, look up its documentation (use context7 if available).
- Check configuration — read config files, environment variables, and infrastructure definitions that affect behavior.
Explore broadly first, then narrow to the relevant areas. Take notes as you go.
Phase 3: Report
Present a structured report to the user:
- Findings — what you discovered, with file paths and line references.
- How it works — trace the relevant code path, explaining the flow.
- Risks — anything concerning: missing tests, edge cases, security issues, performance bottlenecks, implicit assumptions.
- Recommended next steps — concrete actions the user could take (e.g., "run
/agent-dashboard:fixto address the null check atsrc/auth.py:42", "run/agent-dashboard:refactorto extract the retry logic into a shared utility").
Gate: The user has received a clear, actionable report. No files were modified.
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.
- 8d ago First seen · 68 lines · 20 tokens per session scan A 09ae09689320
investigate is a skill published in the GitHub repository bjornjee/agent-dashboard (21 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 625 once invoked, about $0.0001 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
aigon-dev-server
Manage dev server - start, stop, logs, list.
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.
dos-unstick
Analyze BLOCKED/DRAIN run history, cluster recurring causes, and propose one structural fix per wedge via dos decisions. Use when a fleet keeps stalling and you want a systemic unblock rather than another manual nudge.
rust-check
Run cargo check on the current Rust project to find compile errors.
debug
Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix. Prefer root-cause over symptom patches.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…