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 momentmaker/kaijutsu --skill unstuckgit clone --depth 1 https://github.com/momentmaker/kaijutsuWrote 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/momentmaker/kaijutsu/unstuck)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/unstuck"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/unstuck/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/momentmaker/kaijutsu/unstuck"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/unstuck.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 | $0.00064 | $0.01801 |
| Opus 5 | $0.00032 | $0.00901 |
| Sonnet 5 | $0.00013 | $0.00360 |
| Haiku 4.5 | $0.00006 | $0.00180 |
Grade A, and why
unstuck 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unstuck
Break out of unproductive loops. Articulate the problem, then either solve it through clarity or escalate systematically.
Step 0.5's iron-law framing + multi-component instrumentation pattern adapted from
obra/superpowers/skills/systematic-debuggingunder MIT.
Step 0: Memory-first
Before asking the user anything, check project memory for prior similar problems:
- Read
MEMORY.mdindex, scan descriptions for matches against the current symptom (error message, stack trace, behavior) - For any matches, read the full memory entry
- If a strong match exists, present it: "We've hit something like this before: . Is this the same problem? If yes, the prior fix was: ."
If the user confirms it's the same problem, jump straight to Step 5 (Solution Capture) — the entry confirms the user already had the answer.
If no match or user says it's different, proceed to Step 0.5.
Memory format follows the project-memory schema — kebab-case slug + YAML frontmatter (name / description / type).
Step 0.5: Gather evidence
Iron law: no fix proposals without root-cause investigation first. Symptom-fixes mask underlying issues and create new bugs. This step is for the AGENT to do legwork BEFORE asking the human articulation questions — so Step 1's discussion is grounded in facts, not memory of facts.
-
Read the actual error message in full.
- Don't paraphrase. Copy the literal stack trace, exit code, log line.
- Note line numbers, file paths, error codes — the message often contains the exact answer.
- If the error was N invocations ago and you don't have it, ask the user to re-run with the failure reproduced.
-
Check recent changes.
git log --oneline -10on suspect filesgit diffagainst last known good- New dependencies, config edits, env-var changes
- The cause is usually in the most recent change, but the SYMPTOM may surface later.
What ships with it
2 files 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.
- 9d ago First seen · 175 lines · 64 tokens per session scan A 746ec23c6415
unstuck is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,801 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
printing-press-polish
Polish a generated CLI to pass verification and become publish-ready. Runs diagnostics (dogfood, verify, scorecard, go vet, gosec), automatically fixes all issues (verify failures, static-analysis findings, dead code, descriptions, README, MCP tool quality), reports the before/after delta, and offers to publish. Use…
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…
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
report
Investigate bugs comprehensively — cascade through trace, capture browser evidence, extract observability data, and prepare or explicitly create a GitHub issue with grounded findings.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.