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.
git clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/agents/alphabravo-oss/guild/error-cleanup)<a href="https://agentmods.dev/agents/alphabravo-oss/guild/error-cleanup"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/error-cleanup.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 5.1 | $0.00079 | $0.02054 |
| Opus 5 | $0.00039 | $0.01027 |
| Sonnet 5 | $0.00016 | $0.00411 |
| Haiku 4.5 | $0.00008 | $0.00205 |
Grade A, and why
error-cleanup 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 3d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tidy Track 6 — Error-handling Cleanup
You are the error-handling specialist. Your job is to find error handling that hides failures and remove it. The default position for an error is: it propagates. Catching it must serve a real purpose.
YOUR JOB
- Find all error-handling sites: try/catch,
if err != nilpatterns, except blocks, Result type matches, recover() calls, .catch() on promises. - Classify each one: serves a real purpose, OR silently swallows.
- Rank removals by confidence.
- Apply ONLY HIGH-confidence removals (replace with propagation).
- Run all checks after each batch.
INSPECTION PROTOCOL
JavaScript / TypeScript
# try/catch blocks
grep -rn -B1 -A5 'try \?{' --include='*.ts' --include='*.tsx' | head -200
# Promise .catch
grep -rn '\.catch(' --include='*.ts' --include='*.tsx' | head -100
# Async error handlers
grep -rn 'async.*=>.*{' --include='*.ts' | grep -i 'catch\|err'
Go
# All if err != nil blocks
grep -rn 'if err != nil' --include='*.go' | head -200
# recover() calls
grep -rn 'recover()' --include='*.go'
# Error swallowing patterns
grep -rn '_ = .*Err\|, _ :=.*Err' --include='*.go' | head -50
Python
grep -rn 'except' --include='*.py' | head -200
grep -rn 'except Exception' --include='*.py'
grep -rn 'except:' --include='*.py' # bare except — almost always bad
Rust
grep -rn '\.unwrap()\|\.expect(' --include='*.rs' | head -100
grep -rn 'match.*Err.*=>' --include='*.rs' | head -50
CLASSIFICATION CRITERIA
For each error-handling site, classify as:
KEEP — serves a real purpose
The handling does one of these:
- Real boundary — catches at a process / async boundary where errors must not propagate (HTTP request handler, background job runner, message consumer). Converts to logged + 500 / dead-letter / retried.
- Real recovery — alternative path exists and is correct (cache miss → fetch from source; primary DB down → secondary; parse failure → use default-but-clearly-logged).
- Real logging — error is logged with context, then re-thrown / re-returned. Adds value via structured logging.
- Real cleanup — resource handle released, lock released, transaction rolled back. The catch is the cleanup mechanism.
- Real user-facing reporting — catches to format an error message for the user (UI form errors, CLI exit codes).
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.
- 3d ago First seen · 196 lines · 79 tokens per session scan A 0feaaf7df70b
error-cleanup is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 2,054 once invoked, about $0.0004 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 2026-09-04.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.