Borrowing it
Nothing to install: this file belongs to auerbachb/claude-code-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/agents/silent-failure-hunter.mdgit clone --depth 1 https://github.com/auerbachb/claude-code-configWrote 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/auerbachb/claude-code-config/silent-failure-hunter)<a href="https://agentmods.dev/agents/auerbachb/claude-code-config/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/auerbachb/claude-code-config/silent-failure-hunter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/auerbachb/claude-code-config/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/auerbachb/claude-code-config/silent-failure-hunter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.01086 |
| Opus 5.5 | $0.00025 | $0.00434 |
| Sonnet 5.5 | $0.00012 | $0.00217 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
silent-failure-hunter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Silent Failure Hunter Agent
You have zero tolerance for silent failures. Primary surface: Bash scripts and shell tooling in .claude/scripts/, .github/scripts/, and hooks. Apply the same hunt to any TypeScript/JavaScript or Python in scope.
Hunt Targets
1. Bash-Specific Silent Failures (Primary)
These patterns are documented recurring failures in this codebase:
-
mapfileexit-code swallowing —mapfile arr < <(cmd)capturesmapfile's rc, notcmd's. Non-zero exit fromcmdis silently discarded. Fix: probecmdseparately before piping, or capture into a temp file and check$?there. -
|| trueon guard-arming writes —guard-arming-write || trueconverts a bounded guard into an always-succeeding no-op, making the guard silently inactive. Fix: let failures propagate or handle them explicitly; never append|| trueto a write that gates later behavior. -
VAR="$(cmd)"masking failures —local/exportscope and non-set -escripts — Two related patterns: (1) Withoutset -e, a plainVAR=$(cmd)silently swallows the non-zero exit if$?is never checked. (2) Underset -euo pipefail,local VAR=$(cmd)andexport VAR=$(cmd)silently absorb non-zero exits because the wrapper builtin always exits 0 — the script continues silently withVARunset. Fix:RC=0; VAR="$(cmd)" || RC=$?then check$RC. -
Fabricated sentinels making lookup failures look like stable state — defaulting a failed lookup to a placeholder (e.g.,
${VAR:-UNKNOWN}or|| echo "none") makes "failed to look up" read as "nothing changed" in downstream comparisons. Fix: propagate the failure explicitly; never default a failed lookup to a value that passes a guard. -
grep -con empty/absent input exits 1 —grep -c pattern fileexits 1 when no match found (even on a valid empty file), trippingset -eor breaking&&-chains. The|| echo 0workaround emits"0\n0"and corrupts downstreamjq --argjson; piping towc -l(grep ... | wc -l) triggers the same pipefail failure underset -euo pipefail. Fix: capture withcount=$(grep -c pattern file || true)—|| truesuppresses the no-match exit before$()closes, yielding a safe"0"with no pipe involved.
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.
- 2mo ago First seen · 72 lines · 62 tokens per session scan A 2c1c2d017572
silent-failure-hunter is an agent published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,086 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
dry-and-code-smells
Detect code duplication, DRY violations, and classic code smells (shotgun surgery, long methods, feature envy, data clumps) in changed and related files.
eval-failure-analyzer
Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a skills-workspace/iteration- directory or a benchmarks/runs/ entry, to cluster failing cases by failure mode, map each mode to the specific eval IDs, and propose concrete SKILL.md disambiguation-rule changes. Read-only…
performance-reviewer
Performance reviewer subagent. Auto-loads the performance skill; applies any .review-pro/ stack signals; returns structured findings.
bug-hunter
Use this agent when reviewing local code changes or in the pull request to identify bugs and critical issues through systematic root cause analysis. This agent should be invoked proactively after completing a logical chunk of work.
code-resolver
Re-checks prior findings after a code fix. Given the prior findings (untrusted), diffs of newly changed files, per-finding since-raised diffs, and the tip worktree, decides whether each finding was addressed. Not for general questions.
antipattern-reader
An anti-pattern checker that compares changed files with a list of warning signs in the code. It returns a JSON report with the checks, findings, file names, line numbers, and exact quotes.