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 agents/morodomi/dev-crew/error-attackergit clone --depth 1 https://github.com/morodomi/dev-crewWhat 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 | $0.00028 | $0.00980 |
| Opus 5 | $0.00014 | $0.00490 |
| Sonnet 5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
error-attacker 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detection Targets
| Type | Description | Pattern |
|---|---|---|
| empty-catch | 空のcatch/exceptブロック | catch (e) {} |
| swallowed-exception | 例外の握りつぶし | except: pass |
| fail-open | 失敗時にオープン | return true on error |
| generic-exception | 汎用例外キャッチ | catch (Exception e) |
| missing-finally | リソース解放漏れ | no finally block |
Framework Detection Patterns
| Framework | Vulnerable Pattern | Safe Pattern |
|---|---|---|
| Java | catch (Exception e) {} | catch (SpecificException e) { log(e); throw; } |
| Python | except: pass | except ValueError as e: logger.error(e) |
| JavaScript | catch (e) {} | catch (e) { console.error(e); throw e; } |
| PHP | catch (Exception $e) {} | catch (SpecificException $e) { Log::error($e); } |
Dangerous Patterns
patterns:
# Empty Catch (CWE-390)
- 'catch\s*\([^)]*\)\s*\{\s*\}' # JS/TS/PHP/Java
- 'except:\s*pass' # Python
- 'except\s+\w+:\s*pass' # Python specific
- 'rescue\s*=>\s*nil' # Ruby
- 'rescue\s*;\s*end' # Ruby empty
# Swallowed Exception (CWE-391)
- 'catch\s*\([^)]*\)\s*\{\s*//.*\s*\}' # Comment only in catch
- 'catch\s*\([^)]*\)\s*\{\s*/\*.*\*/\s*\}' # Block comment only
- 'except.*:\s*#.*\n\s*pass' # Python with comment
# Fail Open (CWE-636)
- 'catch\s*\([^)]*\)\s*\{[^}]*return\s+true'
- 'except.*:\s*return\s+True'
- 'rescue.*return\s+true'
- 'on\s+error\s+resume\s+next' # VB
# Generic Exception (CWE-396)
- 'catch\s*\(\s*Exception\s+\$?\w+\s*\)' # PHP/Java
- 'catch\s*\(\s*Throwable\s+\w+\s*\)' # Java
- 'except\s+Exception\s*:' # Python
- 'except\s+BaseException\s*:' # Python
- 'catch\s*\(\s*\w+\s*\)\s*\{' # JS catch any
# Missing Finally (CWE-404)
- 'try\s*\{[^}]*\}\s*catch[^f]*$' # Try-catch without finally
Output
Base: {metadata: {scan_id, scanned_at, agent}, vulnerabilities: [{id, type, vulnerability_class, cwe_id, severity, file, line, code, description, remediation}], summary: {total, critical, high, medium, low}}
Extra: prefix=ERR, types=empty-catch|swallowed-exception|fail-open|generic-exception|missing-finally
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 · 89 lines · 28 tokens per session scan A 30070ea73d9a
error-attacker is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 980 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 2026-08-31.
Other agents, from other repositories
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.