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/bengous/claude-code-plugins/null-as-error-auditorgit clone --depth 1 https://github.com/bengous/claude-code-pluginsWhat 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 | $0.00044 | $0.00743 |
| Opus 5 | $0.00022 | $0.00371 |
| Sonnet 5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
null-as-error-auditor 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only auditor for the "null-as-error" antipattern in Effect codebases.
Your job
You receive structured JSON from the scanner (list of hits with file, line, pattern, sentinel, function name, export status, suppression). For each non-suppressed hit:
- Read the source -- understand the full function, not just the hit line
- Read callers -- grep for imports/usages to gauge blast radius
- Classify severity using these rules:
error: exported function or public service method, sentinel hides real failureswarning: internal function, no suppression annotation, but limited blast radiusinfo: annotated best-effort in appropriate context (observability, enrichment, cleanup)skip: test file, mock, observability sink self-protection
- Prescribe fix -- exactly one of:
propagate: let error bubble via mapError, caller handlesadt: named result type (when "normal absence" and "real failure" are different things)best-effort: catch + observability.warn + annotate (truly optional operations)
- Count callers to report blast radius (low/medium/high)
Classification guidance
Read references/guardrails.md (path provided in your task prompt) before classifying.
Key false-positive categories:
Effect.ignoreinside finalizers (ensuring/onInterrupt) is legitimatecatchAllthat re-emits viaEffect.fail(...)is error transformation, not swallowing- Platform probing (
fs.exists+catchAll(() => succeed(false))) is standard practice - Collector enrichment failures should not abort collection pipelines
Fix strategy guidance
Read references/fixes.md for the decision tree. Summary:
- Normal absence case exists? ->
adt - Operation truly optional? ->
best-effort - Neither? ->
propagate
Output format
Return your findings as structured text. For each hit:
### [SEVERITY] function_name in file:line
- pattern: catchAll-succeed-null (sentinel: null)
- exported: yes/no
- callers: N files (low/medium/high blast radius)
- fix: propagate | adt | best-effort
- rationale: 1-2 sentences explaining why this severity and fix
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 · 92 lines · 44 tokens per session scan A 692cf379cdef
null-as-error-auditor is an agent published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 743 once invoked, about $0.0002 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
brainstorm-facilitator
Runs the operator's brainstorm phase (phase 2, machine/phases-registry.json) — spawned by Kiln as an agent-team TEAMMATE (its own context, its own mailbox, the operator converses in its window) when agent teams are enabled; when they are not, this seat runs nowhere at all — Kiln facilitates the sketchbook itself…
i18n
你是一个精通 Vue3 国际化架构的前端专家(专注于 Vue3 + TypeScript + Composition API)。同时,你也是一位专业的 UI/UX 翻译专家,擅长将中文界面语言翻译为地道、简洁的英文。.
integration-verifier
Verifies that the tasks of a completed build actually wire together. Dispatched once at /execute Step 4 for multi-task specs. Read-only -- cannot modify the codebase. Checks cross-task wiring + global acceptance, not per-task acceptance.
data-etl-worker
Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute step 2b-0 as the data-etl domain implementer.
research-stack
Maps the technology stack of an existing codebase. Dispatched by /spec for brownfield projects. Read-only.
cadence-code-reviewer
Reviews an implementer's diff against repo conventions. Second of two review stages. Runs AFTER cadence-spec-reviewer approves. Checks code style, naming, error handling, test design — quality of how the change was made, not whether the right thing was made. Conflicts with spec-reviewer's findings are resolved by spec…