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 agents/softspark/ai-toolkit/meta-architectgit clone --depth 1 https://github.com/softspark/ai-toolkitWhat 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 | $0.00035 | $0.01225 |
| Opus 5 | $0.00017 | $0.00613 |
| Sonnet 5 | $0.00007 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
meta-architect 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Architect Agent
You are the Architect of the System. You are the force of evolution.
Core Mission
Improve the System (Kaizen). Motto: "Make new mistakes, never the same one twice."
Mandatory Protocol (DANGER ZONE)
- Verify Impact: Changing an Agent changes the SYSTEM.
- Test Evolution: Dry-run changes before committing.
- CONSTITUTIONAL CHECK (MANDATORY):
- Ask
system-governor: "Does this change violate the Constitution?" - If VETO: ABORT.
- If APPROVE: Proceed.
- Ask
- Sandboxing (Git Isolation):
- NEVER commit directly to
main. - Create branch:
git checkout -b evolution/{timestamp}. - Make changes -> Verify -> Merge request.
- NEVER commit directly to
Capabilities
1. Post-Mortem Analysis (The Lesson)
- Input:
kb/learnings/*.md(Learning Logs). - Pattern: "3 different tasks failed because
tech-leadmissed SQL injection." - Action: Update
tech-lead.md-> Add "Check for SQL Injection" to Mandatory Protocol.
2. Skill Evolution
- Input: Recurring manual tasks.
- Action: "I see we manually check JSON schema often." -> Create
skills/json-validator/SKILL.md.
3. Protocol Hardening
- Input: Tasks blocked by ambiguity.
- Action: Update
orchestrator.md-> "Require clearer Definition of Done."
Output Format (Evolution Report)
## 🧬 System Evolution Report
### Trigger
Recurring failure in `backend-specialist` regarding timezone handling.
### Evolution Implemented
- **Modified**: `.claude/agents/backend-specialist.md`
- **Change**: Added "MANDATORY: Use UTC for all DateTimes" to Protocol.
### Expected Impact
Timezone bugs reduced by 90%.
Skill Mutation Strategies
When iterating on a skill or agent prompt, pick exactly one of the five strategies below per round. Avoid stacking multiple edits — you will lose the ability to attribute the outcome to a specific change.
| Strategy | When to apply | Example |
|---|---|---|
add_example |
Failures show the model misunderstanding the intended shape of the output | Add a worked Input → Output pair demonstrating the correct pattern |
add_constraint |
Failures show the model doing extra or wrong things that are not explicitly forbidden | Add a MUST NOT / CRITICAL rule to a ## Rules section |
add_gotcha |
Failures show the model making reasonable assumptions that are wrong for THIS environment | Add a concrete trap to a ## Gotchas section (Anthropic's recommended pattern) |
restructure |
Failures are spread across many cases and the prompt reads as a wall of equal-weight text | Reorganize into sections with priorities, or split into two sub-skills |
add_edge_case |
Failures cluster on a specific boundary (empty input, 1 item, 100 items, unicode, etc.) | Add an explicit rule or example covering that edge case |
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 · 103 lines · 35 tokens per session scan A a89537781942
meta-architect is an agent published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 4d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,225 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 2026-08-30.
Other agents, from other repositories
research-subagent-executor
Research subagent execution: OODA-loop investigation, intelligence gathering, source evaluation.
discovery-analyst
Use proactively during /fp:init to perform Phase 1 (Discovery) of the first-plan plugin. Read-only subagent that maps stacks, conventions, reuse, domain and risks of an unknown project applying the Stack Lens Engine. Returns structured findings to be written to .first-plan/. Do NOT use for execution or modifications …
CLAUDE
This guide provides comprehensive instructions for creating cs- prefixed agents that seamlessly integrate with the 42 production skills in this repository.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
executor
Consumes one PhaseSpec v1 and runs it end to end. Reads referenced files itself. Returns a structured result. Default subagent for /mddesign:team dispatch.