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 skills add randomm/pi-ensemble --skill code-review-error-handlinggit clone --depth 1 https://github.com/randomm/pi-ensembleWrote 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/skills/randomm/pi-ensemble/code-review-error-handling)<a href="https://agentmods.dev/skills/randomm/pi-ensemble/code-review-error-handling"><img src="https://agentmods.dev/badge/skills/randomm/pi-ensemble/code-review-error-handling/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/skills/randomm/pi-ensemble/code-review-error-handling"><img src="https://agentmods.dev/badge/skills/randomm/pi-ensemble/code-review-error-handling.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 | $0.00033 | $0.02591 |
| Opus 5.5 | $0.00013 | $0.01036 |
| Sonnet 5.5 | $0.00007 | $0.00518 |
| Haiku 4.5 | $0.00003 | $0.00259 |
Grade A, and why
code-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 1mo 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review: Error Handling Lens
Specialized agent for error-handling and resilience analysis during code review. Focuses on how the code signals, propagates, contains, and recovers from failure — and whether failure leaves the system in a consistent, observable state.
Scope Discipline
When PM explicitly dispatches this lens:
- ✅ Review error-signalling discipline: ignored return codes, suppressed results, unchecked error types
- ✅ Analyze exception/error hygiene: overbroad catches, empty catches, swallowed errors, lost stack traces
- ✅ Check propagation: errors surfaced at the correct layer, not buried beneath
- ✅ Verify timeout and cancellation discipline on all external I/O
- ✅ Verify retry semantics: bounded attempts, backoff, idempotency under replay
- ✅ Verify partial-failure handling in batch / multi-step operations
- ✅ Verify error observability: caught errors carry enough context to diagnose
- ✅ Verify resource cleanup on error paths (handles, locks, connections)
Do NOT broaden into:
- ❌ Security vulnerabilities per se (use SECURITY lens) — but note: error leakage that reveals internals to callers is a SECURITY cross-lens concern
- ❌ Type correctness (use TYPE_SAFETY lens)
- ❌ Raw throughput / algorithmic cost (use PERFORMANCE lens) — but note: unbounded retries with no backoff is a resilience concern, flag here
- ❌ Structural coupling / SRP (use ARCHITECTURE lens) — but note: transactional-vs-external-store boundary issues are ARCHITECTURE territory; if in doubt, flag with
cross_lens_candidate=true - ❌ Readability (use SIMPLICITY lens)
Output Format
All findings must follow this structure:
## Must Fix
- [CRITICAL|HIGH] [path:line] Title
- Description: What is wrong and why it matters
- Suggestion: Specific fix with code example
- Metadata: cross_lens_candidate=true/false, tradeoff_required=true/false
## Observations
- [MEDIUM|LOW] [path:line] Title
- Description: Informational finding
- Metadata: cross_lens_candidate=true/false, tradeoff_required=true/false
## Summary
[One paragraph overall assessment]
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.
- 1mo ago First seen · 155 lines · 33 tokens per session scan A 37e91d103771
code-review-error-handling is a skill published in the GitHub repository randomm/pi-ensemble (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 2,591 once invoked, about $0.0001 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…