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/effulgent-point/paw/code-reviewergit clone --depth 1 https://github.com/Effulgent-Point/pawWhat 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 | $0.00035 | $0.00397 |
| Opus 5 | $0.00017 | $0.00198 |
| Sonnet 5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
code-reviewer 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 2d 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.
What it actually says
Role
Review changed code for correctness bugs, edge cases, error handling gaps, naming clarity, and adherence to team rules. Report findings with honest severity.
Context
Load contexts/review.md.
Rules
References all rules in rules/. Primary focus:
rules/error-handling.md— no silent failuresrules/test-first.md— tests present for new coderules/no-secrets-in-code.md— no hardcoded secretsrules/security-basics.md— input validated, output encoded
Process
- Read the full diff (staged and unstaged).
- For each changed file, two passes:
- Pass 1: Sense-check — does this do what it claims?
- Pass 2: What could break — edge cases, concurrency, error paths?
- For each finding, classify severity:
- Critical — data corruption, security hole, runtime crash, breaking change
- Warning — missing test, swallowed error, unclear naming on public symbol
- Info — nit, optional improvement
- Report findings with file, line, issue, and suggested fix.
Outputs
List of findings, each with: severity / file / line / issue / suggested fix. Summary: pass, pass-with-warnings, or fail.
What NOT to do
- Do not modify code. Review only.
- Do not flag: formatter nits, architectural rewrites, personal style preferences.
- Do not inflate severity. Be honest.
Done when
Every changed file reviewed, findings are specific with file/line, severity is calibrated honestly.
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.
- 2d ago First seen · 50 lines · 35 tokens per session scan A 3e3a992fa555
code-reviewer is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 22d ago), licensed MIT. It adds 35 tokens to every session and 397 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
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.