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/lagz0ne/c3-skill/workgit clone --depth 1 https://github.com/lagz0ne/c3-skillWhat 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 | $0.00010 | $0.00863 |
| Opus 5 | $0.00005 | $0.00432 |
| Sonnet 5 | $0.00002 | $0.00173 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
work 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/work Command
Arguments
$ARGUMENTS
Intent Detection
Analyze $ARGUMENTS to determine intent:
| Intent | Patterns | Focus |
|---|---|---|
| Change | "improve", "add", "build", "work on", "implement", "create", "enhance" | What should exist |
| Troubleshoot | "off", "broken", "wrong", "failing", "not working", "weird", "bug" | What's going wrong |
Phase 1: Context Gathering (inline)
Load project understanding before launching subagents:
CLAUDE.md + references/skill-harness.md (principles)
skills/**/*.md (all skills, their connections)
git status (current state)
Summarize: What is the current state relevant to $ARGUMENTS?
Phase 2: Brainstorming (subagent)
Launch subagent with superpowers:brainstorming:
Input: Context summary + $ARGUMENTS + detected intent Goal: Pin-point the actual question/goal through socratic dialogue Output: Clear problem statement + proposed approach
If later phases find complexity, this phase may be revisited.
Phase 3: Testing Strategy (subagent)
Launch subagent to discover how to verify the work:
Input: Brainstorm output (goal + approach) Method: Socratic questioning
Questions to answer:
- How would you know it works?
- What's the simplest check?
- What breaks if this is wrong?
- What existing tests/patterns can we reuse?
Output criteria - test approach must be:
- Fast (seconds, not minutes)
- Good coverage (key paths)
- Cheap to maintain (minimal fixtures)
- Human readable (clear pass/fail)
Loop back to brainstorming if: approach is too complex to test practically
Phase 4: Writing Plans (subagent)
Launch subagent with superpowers:writing-plans:
Input: Brainstorm output + testing strategy
Output: Two separate plans in docs/plans/:
YYYY-MM-DD-<topic>-implementation.md- Implementation stepsYYYY-MM-DD-<topic>-test.md- Test plan with verification steps
Loop back if:
- Scope issue discovered → return to brainstorming
- Test gap found → return to testing strategy
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 · 122 lines · 10 tokens per session scan A 5c1f1a6dd92c
work is a command published in the GitHub repository lagz0ne/c3-skill (12 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 863 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.