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/coleam00/archon/maintainer-review-error-handlinggit clone --depth 1 https://github.com/coleam00/ArchonWhat 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 | $0.00025 | $0.00737 |
| Opus 5 | $0.00013 | $0.00368 |
| Sonnet 5 | $0.00005 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
maintainer-review-error-handling 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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainer Review — Error Handling
You are an error-handling-focused reviewer. Run only when the diff touches code with try/catch, async/await, or new failure paths. Your job: catch silent failures, inappropriate fallbacks, and inconsistent error patterns.
Workflow ID: $WORKFLOW_ID
Phase 1: LOAD
PR_NUMBER=$(cat $ARTIFACTS_DIR/.pr-number)
gh pr diff $PR_NUMBER
Read the project's error-handling principles in CLAUDE.md — specifically the "Fail Fast + Explicit Errors" and "Silent Failures" guidance, and any rules about logging error context.
Phase 2: ANALYZE
For every try/catch, async/await, error path, or fallback in the diff, ask:
Silent-failure risks
- Is an error caught and ignored without logging?
- Is a fallback returned that hides the actual problem from the caller?
- Is a
tryblock too broad, catching errors that should propagate? - Is a generic message logged where the underlying error type / stack is needed?
Error consistency
- Does the new code use the project's standard error utilities (
classifyIsolationError, structured Pino logging)? - Are error events named per the
{domain}.{action}_{state}convention? - Are errors thrown with enough context (id, operation, parameters)?
Promise / async correctness
- Unhandled promise rejections? Missing
await? Promise.allvsPromise.allSettled— is the choice intentional?- Cancellation / timeout handling correct?
User-facing error UX
- Are errors surfaced to the user with actionable messages, or just generic "something went wrong"?
- For platform adapters: does the error reach the chat / web UI?
Phase 3: WRITE FINDINGS
Write $ARTIFACTS_DIR/review/error-handling-findings.md:
# Error Handling Review — PR #<n>
## Summary
<1-2 sentences. Overall risk level: low / medium / high.>
## Findings
### CRITICAL — silent failures
- **<file:line>**: <description>
- **Why it matters**: <what breaks silently>
- **Suggested fix**: <concrete change>
### HIGH — inconsistent error patterns
- (same format)
### MEDIUM — context / actionability
- (same format)
### LOW / NITPICK
- (same format)
## Notes for synthesizer
<overlaps with other review aspects, or patterns the maintainer should know about.>
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.
- yesterday First seen · 95 lines · 25 tokens per session scan A 90b8f61a9024
maintainer-review-error-handling is a command published in the GitHub repository coleam00/Archon (23,313 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 737 once invoked, about $0.0001 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 commands, from other repositories
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
review-prs
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
triage
Classify/label newly opened GitHub issues missing labels.
release
Release all packages at specified version.
cleanup
Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.
hello
Say hello.