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 skills/zjunlp/mechanist/auto-iteration-loopnpx skills add zjunlp/Mechanist --skill auto-iteration-loopgit clone --depth 1 https://github.com/zjunlp/MechanistWrote 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/zjunlp/mechanist/auto-iteration-loop)<a href="https://agentmods.dev/skills/zjunlp/mechanist/auto-iteration-loop"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/auto-iteration-loop.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00114 | $0.19489 |
| Opus 5 | $0.00057 | $0.09745 |
| Sonnet 5 | $0.00023 | $0.03898 |
| Haiku 4.5 | $0.00011 | $0.01949 |
Grade B, and why
auto-iteration-loop scanned grade B with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
2. **User MCP config** — `~/.claude/settings.json`, same field. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads MCP configurationlowAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
1. **Project MCP config** — `${PROJECT_ROOT}/.mcp.json`, field `mcpServers["llm-chat"].env.{LLM_MODEL,LLM_BASE_URL,LLM_API_KEY}`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Fallback: curl** How it starts
The opening of the file, as written. The whole thing — 849 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Iteration Loop: Adversarial Review with Bounded Back-Edges
Autonomously iterate over /auto-verify's per-claim verdicts: review → implement fixes (variant-integrity, main-experiment-script, or claim-stage rewrite) → re-review, until the external reviewer gives a positive assessment with all FAIL / INCONCLUSIVE / ZERO_ELIGIBLE_VARIANTS claims resolved, or the iteration budget is exhausted.
Context: $ARGUMENTS
Constants
-
MAX_ITERATIONS = 6 — Hard upper bound on total back-edge actions across the whole loop. Each of the following consumes 1 iteration, regardless of which Phase A→E cycle they fall in:
- ① variant-only fix → re-run
/auto-verify <claim-id> — resume: true - ② main-experiment-script /
EXPERIMENT_PLAN.mdfix → re-run/auto-experiment(optionally followed by/auto-verifychain) - ③ claim-stage re-entry → rewrite claim (full
/auto-claiminvocation OR lightweight in-loop rewrite) → re-run downstream stages
Pure reviewer cycles that change nothing on disk (no new experiments, no claim changes) do not consume iterations. PASS-claim consistency checks and deferred-claim recording do not consume iterations. New claims produced by ③ inherit the same budget — they do not get a fresh
MAX_ITERATIONSof their own. Override viaMAX_ITERATIONS:arg fromagents/iteration.md.Resource-Fidelity invariant (all back-edges). If
refine-logs/FINAL_PROPOSAL.md/refine-logs/EXPERIMENT_PLAN.mdcarry aresource_fidelity: strictmarker (the reproduction combination —behavior-source:given+mechanism:given), every back-edge MUST preserve it: when editingEXPERIMENT_PLAN.md(type ②) or any claim rewrite (type ③), keep the top-of-fileresource_fidelity:line verbatim — never drop, comment out, or change it. Dropping the marker silently disables the harness, re-opening the door to smaller-model swaps and data subsetting the harness exists to prevent. For type-③ full re-entry, detect the original run's axes fromidea-stage/IDEA_REPORT.md's**Behavior-source**:/**Mechanism**:headers (or directly from theresource_fidelity: strictmarker) and pass bothbehavior_sourceandmechanisminto the queuedauto-claimcall so a reproduction-combo re-entry staysgiven+given(the new run re-stamps theresource_fidelity: strictmarker automatically — it is marker-driven, not a flag). - ① variant-only fix → re-run
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.
- 4d ago First seen · 849 lines · 114 tokens per session scan B cee822a43389
auto-iteration-loop is a skill published in the GitHub repository zjunlp/Mechanist (51 stars, last pushed 8d ago), licensed MIT. It adds 114 tokens to every session and 19,489 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 3 findings (reads agent configuration directories, reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
create-atomic-tool
Build a BaseTool[InSchema, OutSchema] subclass — input/output schemas, BaseToolConfig, run() (and optional runasync()), env-driven secrets, typed failure outputs. Use when the user asks to "add a tool", "create a tool", "wrap an API as a tool", "build a BaseTool", "make a calculator/search/weather tool", or runs…
framework
Guide for the Atomic Agents Python framework — schemas, agents, tools, context providers, prompts, orchestration, and provider configuration. Use when code imports from atomicagents, defines an AtomicAgent, BaseTool, or BaseIOSchema, or the user asks about multi-agent orchestration or LLM-provider wiring in an…
create-atomic-agent
Build and wire an AtomicAgent[InSchema, OutSchema] — schemas, AgentConfig, SystemPromptGenerator, provider client, history, hooks, optional context providers. Use when the user asks to "create an agent", "add another agent", "build an AtomicAgent", "wire up an agent", "make a planner/router/extractor agent", or runs…
create-atomic-context-provider
Build a BaseDynamicContextProvider that injects a named, titled block into an agent's system prompt at every run() — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to "add a context provider", "inject X into the prompt", "give the agent dynamic context", "wire…
create-atomic-schema
Design and write a BaseIOSchema input/output pair for an Atomic Agents agent or tool — docstrings, field descriptions, validators, error variants. Use when the user asks to "create a schema", "design the input/output schema", "define an IOSchema", "write a BaseIOSchema", "model the agent's output", or runs…
new-app
Scaffold a new Atomic Agents project from scratch — create the directory, pyproject.toml, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs /atomic-agents:new-app.