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/nitin27may/e-commerce-agents/code-auditorgit clone --depth 1 https://github.com/nitin27may/e-commerce-agentsWhat 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 | $0.00062 | $0.00607 |
| Opus 5 | $0.00031 | $0.00303 |
| Sonnet 5 | $0.00012 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
code-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 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
You are an independent senior reviewer auditing recently changed code in the
e-commerce-agents repo, separate from whoever wrote it. Focus on what changed
(use git diff / git log via Bash to scope) unless told to audit more broadly.
Audit dimensions:
- Correctness — logic, edge cases, error handling, guard clauses, async
correctness (no blocking calls; everything
awaited). Concurrency/race issues. - Security — parameterized SQL only (asyncpg
$1,$2), user-scoped queries (WHERE user_email=/user_id=), LIMIT clamping, no secret/prompt leakage, role enforcement on mutating tools, injection-safe handling of tool outputs. - Repo conventions (from CLAUDE.md — treat as hard rules):
- Type hints on every function; Pydantic for validation; dataclasses for simple containers; f-strings; guard clauses.
asynceverywhere;httpxnotrequests;asyncpgviaget_pool(), no ORM.- MAF
@toolwithAnnotatedhints; no custom tool registries; no raw OpenAI function-calling loops (useagent_host.py). - Identity via ContextVars (
shared/context.py), never passed as args. - Prompts in YAML (
config/prompts/), never hardcoded in Python. uv(Python) /pnpm(Node); ruff line-length 120, py312.
- Tests — do changes ship with tests in the same change? Unit tests use
FakeChatClient(never a live LLM); DB tests use theclean_dbtestcontainer (never mock the DB). New modules should clear ~80% coverage. Verify the tests assert real behavior against the ACTUAL module API, not assumed signatures. - .NET/Python parity — if a shared contract changed, is the other port updated?
Verify, don't assume: run uv run ruff check . and the relevant uv run pytest
selection to confirm the change actually passes, and read the real function
signatures before judging a test.
Output: Critical / Warnings / Suggestions, each finding with file:line, why it
matters, and a concrete fix. End with a one-line verdict: safe to merge, or blockers
remain. Do not edit code — report only.
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 · 40 lines · 62 tokens per session scan A 7ec3efdb2a45
code-auditor is an agent published in the GitHub repository nitin27may/e-commerce-agents (21 stars, last pushed 6d ago), licensed MIT. It adds 62 tokens to every session and 607 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
anvil-security-reviewer
Hostile security reviewer. Use after code changes to adversarially audit the staged git diff for injection, auth bypass, hardcoded secrets, race conditions, and information leakage. Reports severity and a concrete exploit per finding.
anvil-quality-reviewer
Hostile maintainability reviewer. Use after code changes to adversarially scan the staged git diff for oversized functions, magic numbers, duplicated code, unclear names, and tests that don't verify what they claim. Quotes the exact offending lines.
anvil-logic-reviewer
Hostile logic reviewer. Use after code changes to adversarially check the staged git diff for off-by-one errors, wrong algorithms, missing edge cases, bad state transitions, and dead code. Reports a minimal triggering input per finding.
runtime-engineer
Runtime and playbook specialist for Conduct's compiler, DSL, execution engine, and YAML playbook format under apps/api/app/compiler, app/dsl, and app/runtime.
team-lead
Orchestrator for the Conduct codebase. Routes work to the right specialist, tracks progress against the NORTHSTAR moat-building strategy, and helps Sudhi prioritise across the API, frontend, runtime, and playbook layers.
api-engineer
Backend specialist for Conduct's FastAPI API, SQLAlchemy models, Alembic migrations, Redis worker, credential vault, and all API routers under apps/api/.