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 softspark/ai-toolkit --skill evolvegit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/evolve)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/evolve"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/evolve/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/softspark/ai-toolkit/evolve"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/evolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00990 |
| Opus 5.5 | $0.00012 | $0.00396 |
| Sonnet 5.5 | $0.00006 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
evolve 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolve Command
$ARGUMENTS
Triggers the Meta-Architect to improve agent and skill definitions based on observed patterns.
Usage
/evolve [source]
# /evolve learnings : analyze kb/learnings/ for recurring failure patterns
# /evolve last-failure : analyze the most recent error log
# /evolve agents : audit all agent definitions for gaps
Protocol
1. Analyze
Read the input source and extract actionable patterns:
- learnings: grep
kb/learnings/for entries taggedfailure,retry,timeout, orinefficiency - last-failure: read the most recent file in
kb/learnings/and identify root cause - agents: scan all
.mdfiles inapp/agents/for missing tools, vague prompts, or mismatched model tiers
2. Design
Draft changes targeting the identified patterns:
| Target | File Location | Change Type |
|---|---|---|
| Agent definitions | app/agents/*.md |
Frontmatter (tools, model), system prompt text |
| Skill definitions | app/skills/*/SKILL.md |
Description, workflow steps, allowed-tools |
| Rules | app/rules/ |
New or updated rule files |
Show the proposed diff to the user before applying.
3. Implement
Apply approved changes. After each edit:
- Run
python3 scripts/validate.pyto confirm structural integrity - Verify YAML frontmatter parses without errors
- Confirm no forbidden patterns (eval, exec, shell=True)
4. Report
Create a summary documenting what evolved:
## Evolution Report
- **Source**: [learnings | last-failure | agents]
- **Pattern found**: [description of failure/inefficiency]
- **Changes applied**:
- `app/agents/[name].md`: [what changed and why]
- **Validation**: passed / failed
Rules
- MUST delegate file edits to the
meta-architectagent — this command is the trigger, the agent owns the changes - MUST have a concrete failure signal (recurring error, named incident, repeated correction) before evolving — do not mutate based on vibes
- NEVER evolve an agent based on a single failure instance — evolution is pattern-matching, not reaction
- NEVER touch
.claude/agents/*files directly from this skill;meta-architectis the only agent with that authority - CRITICAL: every evolution names the trigger, the change, and the expected measurable shift (e.g., "reduces false routing of
/debugto/fix") - MANDATORY: run
scripts/validate.py --strictafter every applied change; roll back if the score drops
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.
- 1mo ago First seen · 93 lines · 31 tokens per session scan A 6df04ffc9c73
evolve is a skill published in the GitHub repository softspark/ai-toolkit (180 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 990 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
cline-openai-cache-key
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.