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/hknc/claude-evolve/helpgit clone --depth 1 https://github.com/hknc/claude-evolveWhat 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 | $0.00033 | $0.00517 |
| Opus 5 | $0.00016 | $0.00259 |
| Sonnet 5 | $0.00007 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
evolve-help 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/evolve help
Output this EXACTLY as shown below. Do not improvise or add content.
Claude Evolve
A toolkit that learns from your sessions and provides personalized guidance.
What Happens Automatically
- Session start: Loads your understanding.md patterns
- During work: Claude flags corrections & insights via
/evolve signal - Session end: Stop hook suggests
/learnif signals pending
Commands You Should Use (Best Results)
| Command | When to Run | What It Does |
|---|---|---|
/evolve signal |
Anytime (Claude does this automatically) | Flags insight for later capture |
/learn |
When signals pending, after discoveries | Extracts signals → agents/skills/rules |
/reflect |
Startup shows "N pending" | Synthesizes observations → understanding.md |
/evolve audit |
Periodically | Reviews setup, suggests improvements |
Other Commands
| Command | Purpose |
|---|---|
/evolve understanding |
View your learned patterns |
/evolve status |
Show toolkit info and git status |
/evolve context |
Analyze project, suggest agents |
/evolve prepare |
Check toolkit before complex tasks |
/workflow |
Show current phase, manage workflow |
/workflow next |
Advance to next phase |
/workflow skip |
Skip current phase |
/workflow done |
Mark workflow complete |
/workflow switch |
Switch between active workflows |
/workflow expand |
Create sub-tasks from phase items |
Setup (one-time)
| Command | Purpose |
|---|---|
/evolve init |
Create or recover toolkit |
/evolve migrate |
Import ~/.claude/ content |
/evolve release |
Push changes to git |
/evolve switch |
Change active toolkit |
The Learning Loop
Work → Claude signals insights → Stop hook saves observations → /reflect → /learn → Work
(automatic) (automatic) (manual) (manual)
↓ ↓
understanding components
.md (agents/skills/rules)
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 · 71 lines · 33 tokens per session scan A ae418917ac79
evolve-help is a command published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 517 once invoked, about $0.0002 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 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.