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 blueberrycongee/termcanvas --skill investigategit clone --depth 1 https://github.com/blueberrycongee/termcanvasWrote 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/blueberrycongee/termcanvas/investigate)<a href="https://agentmods.dev/skills/blueberrycongee/termcanvas/investigate"><img src="https://agentmods.dev/badge/skills/blueberrycongee/termcanvas/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/blueberrycongee/termcanvas/investigate"><img src="https://agentmods.dev/badge/skills/blueberrycongee/termcanvas/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 | $0.00053 | $0.00523 |
| Opus 5 | $0.00026 | $0.00262 |
| Sonnet 5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
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 9d 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
Investigate
Systematic debugging workflow. Do not guess-and-fix — find the root cause first.
Phase 1: Collect
Gather all available evidence before forming any hypothesis.
- Read the error message, stack trace, or symptom description exactly as given
- Identify the affected code path — read the relevant source files
- Check
git log --oneline -20in the affected area for recent changes - If reproducible, reproduce the issue and capture the exact output
- List what you know and what you do not know
Deliverable: a structured symptom summary with affected files, error output, and recent changes.
Phase 2: Hypothesize
Form up to 3 ranked hypotheses. For each:
- State the hypothesis in one sentence
- Identify the single cheapest check that would confirm or refute it
- Do NOT start fixing yet
Phase 3: Verify
Test hypotheses in rank order. For each:
- Run the cheapest check identified in Phase 2
- If confirmed — move to Phase 4
- If refuted — record what you learned and move to the next hypothesis
3-strike rule: If all 3 hypotheses fail, step back and re-collect. Do not keep guessing. Re-read the code path more carefully, expand the search area, or check for environmental factors (config, dependencies, platform).
Phase 4: Fix
Only after root cause is confirmed:
- Write the minimal fix that addresses the root cause
- Do not refactor surrounding code
- Do not add speculative defensive checks
- Run the test suite to verify the fix and check for regressions
Phase 5: Verify and Report
- Confirm the original symptom is resolved
- Confirm no regressions were introduced
- Summarize: root cause, fix applied, evidence of resolution
Rules
- Never skip Phase 1-3 and jump to fixing
- Never change tests to match broken behavior
- If the bug is in a dependency or environment, report it — do not patch around it silently
- If you cannot reproduce the issue, say so and explain what you tried
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.
- 9d ago First seen · 67 lines · 53 tokens per session scan A 5f1dbb250e45
investigate is a skill published in the GitHub repository blueberrycongee/termcanvas (394 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 523 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
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
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.
add-plugin
Use when installing, disabling, enabling, or troubleshooting a third-party octomux plugin — the manifest row shape, octomux plugins list/disable/enable, reading octomux doctor output, and recovering a broken boot with --safe-mode.
create-task
Use when creating an octomux task to dispatch autonomous Claude Code agents for building features, fixing bugs, or any code changes.
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.
ward
Ward the codebase — an ad-hoc test-gap audit that reveals unguarded code (untested functions, uncovered edge cases, missing error-handling and integration tests) and conjures ready-to-paste test skeletons as protective wards against regression, surfaced inline in the session. Scoped to your current diff by default, or…