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 agentmods add commands/apexiq/skillsmith/debuggit clone --depth 1 https://github.com/ApexIQ/skillsmithWhat 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 | $0.00000 | $0.00541 |
| Opus 5 | $0.00000 | $0.00270 |
| Sonnet 5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
debug 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 2d 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.
This is a copy
80% identical to align — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command: /debug
This command is powered by a dynamic Skillsmith workflow bundle.
Goal
debug complex runtime issues for library click, pytest, arch-business-logic, arch-ui, arch-unknown
Resources
- Workflow Bundle: .agent/workflows/debug.md
- Top Skills: notebooklm, javascript_testing_patterns, makepad_skills, context7_auto_research, typescript_expert
Execution Plan
- Read .agent/project_profile.yaml and .agent/context/project-context.md.
- Confirm the requested goal against the current project stage and target tools.
- [AND] Discover stage: Read .agent/project_profile.yaml and .agent/context/project-context.md before taking action. Acceptance: Project profile and generated context are present or inferred without error.; The ranked skill list is deterministic for the current goal and profile..
- [OR] Plan stage: Turn the goal into a minimal patch plan with explicit verification checkpoints. Acceptance: The plan names concrete files, commands, or subsystems.; Every planned step has at least one verification check..
- [OR] Build stage: Implement the smallest coherent change needed for the goal. Acceptance: Reproduce the issue and capture the failing behavior before the fix is applied.; Implement the fix with focused verification for the affected area..
- [AND] Review stage: Inspect the changed files for correctness, regressions, and missing coverage. Acceptance: The review names concrete risks or confirms the change is safe.; The review output is ordered and actionable for the next agent..
- [AND] Test stage: Run the relevant automated tests for the changed workflow behavior. Acceptance: Targeted tests pass after the implementation change.; The failure mode is observable if the stage structure regresses..
- [AND] Ship stage: Make the workflow output usable as a release-grade handoff artifact. Acceptance: The generated workflow includes both stage structure and the legacy
stepslist.; Compose output remains stable across repeated runs with the same inputs.. - [AND] Reflect stage: Summarize what the evidence says about the current run. Acceptance: Reflection text is grounded in the run's actual feedback or retry state.; Any mode suggestion comes from the current evidence, not a dummy rule..
- Load the top relevant skills: notebooklm, javascript_testing_patterns, makepad_skills, context7_auto_research, typescript_expert.
- Verification loop: run 1 verification pass before completion.
- Run the most relevant test or validation command before completion.
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.
- 2d ago First seen · 28 lines · 0 tokens per session scan A 1c6f02b0ce70
debug is a command published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 541 tokens. A static security scan graded it A with 0 findings. It is 80% identical to align, differing in 12 lines, and is treated as a copy.
Other commands, from other repositories
become
Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue, and instincts.
notebook
Low-ceremony capture for ideas (half-formed, want to mature into stories), todos (concrete actions), and notes (durable project/team facts for future recall). One-line capture, conditional elaboration AUQ. Use BEFORE thoughts get forced into stories.
cycle-design
Design a cycle — create new cycles with planned stories, detail existing planning cycles, or quick-sketch a roadmap. Detects planning docs in .craft/planning/ and sources the cycle from them when relevant.
cycle-start
Activate a cycle and start implementing its stories.
docs
Generate or update project documentation using the crystallized doc-writer agent. Two-pass: brief (analysis + plan) then generate (write docs). Detects first-run vs update automatically.
reflect
Apply captured learnings to improve the Craft harness and project patterns. Converts .learnings.yaml into permanent updates.