Operations
Agent Toolchain Health Check
Check the harness before blaming the model.
Use when
Agent setup depends on CLIs, MCP servers, browsers, tokens, local models, and cron jobs.
Cadence
Weekly or before a heavy agent run
Verification
Critical tools authenticate, return sane output, and have a known fallback or blocker owner.
Structured loop spec
| Field | Value |
|---|---|
| Name | Agent Toolchain Health Check |
| Category | Operations |
| Trigger | Weekly or before a heavy agent run |
| Objective | Check the harness before blaming the model. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Define the exact scope, source of truth, and approval boundary.; Inspect current state and rank the highest-risk gap.; Make one small, reversible improvement.; Run the stated verification and record evidence.; Stop on success, budget, no progress, or approval required. |
| Verification | Critical tools authenticate, return sane output, and have a known fallback or blocker owner. |
| Stop condition | Stop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required. |
| Budget | Set a time, turn, token, retry, file, or dollar cap before running the loop. |
| Approval boundary | Human approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments. |
| Safe output | Draft, report, checklist, table, or approval-gated recommendation |
| Works with | Claude, ChatGPT, Gemini, any tool-using AI assistant |
Steps
- Define the exact scope, source of truth, and approval boundary.
- Inspect current state and rank the highest-risk gap.
- Make one small, reversible improvement.
- Run the stated verification and record evidence.
- Stop on success, budget, no progress, or approval required.
Prompt
Run the Agent Toolchain Health Check loop. Use it when Agent setup depends on CLIs, MCP servers, browsers, tokens, local models, and cron jobs. Work in bounded iterations: inspect current state, choose the highest-risk gap, make one reversible improvement, verify it, and record evidence. Stop when Critical tools authenticate, return sane output, and have a known fallback or blocker owner. or when blocked, budget exhausted, or approval is required.Run in Claude Code
Paste this into Claude Code (or any tool-using agent) to run the loop bounded: one change per round, the same verification every round, durable state files, and explicit stop conditions.
Run the "Agent Toolchain Health Check" loop from AI Loop Library (https://ailooplibrary.com/loops/toolchain-health-check/) as a bounded loop.
Goal: Check the harness before blaming the model.
Rules: one change per round; run the same verification every round (Critical tools authenticate, return sane output, and have a known fallback or blocker owner.); append each round to docs/loops/toolchain-health-check/progress.md and update docs/loops/toolchain-health-check/state.json; stop on verifier pass, 8 rounds, 3 consecutive failed verifications, no progress, a blocker, or anything needing human approval (money, production, outbound, deletion). Finish with a proof report: rounds used, changes made, verification output, remaining risk, and the next human decision.