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 skills/jl-cmd/claude-dev-env/e-code-reviewnpx skills add jl-cmd/claude-dev-env --skill e-code-reviewgit clone --depth 1 https://github.com/jl-cmd/claude-dev-envWhat 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 | $0.00092 | $0.01831 |
| Opus 5 | $0.00046 | $0.00915 |
| Sonnet 5 | $0.00018 | $0.00366 |
| Haiku 4.5 | $0.00009 | $0.00183 |
Grade A, and why
e-code-review 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
e-code-review
Pick a level, run that review, optionally fix and loop. Each level has its own procedure file. Fix application lives in reference/fix.md; repeat-until-clean lives in reference/loop.md.
Mode routing
Resolve the first matching invocation before the normal refusal and loop rules:
preflight-proposalrequires<pr_number>,--level <low|medium|xhigh>,--base-sha <immutable SHA>,--head-sha <immutable SHA>, and--worktree <isolated path>. The caller supplieslowas the default level;mediumandxhighare valid selections. Route the selected mode through reference/preflight-proposal.md to establish proposal context. The mode runs<review_level> --fix looplocally and returns selected-candidate-ready proposal evidence.- Normal mode follows the current level,
--fix, andloopbehavior.
The proposal mode applies the canonical proposal contract at @~/.claude/_shared/pr-loop/preflight-proposal.md. The local extension selects the review level and records finding outcomes. The downstream owner records selected proposal IDs before reapplication; each new finding receives a new ID.
Gotchas
lowstays single-pass. No subagents, no full-file reads: one read pass per target item, one findings pass.- Collection reports every real finding. Keep every CONFIRMED or PLAUSIBLE finding at its assigned severity (
blocker,high,medium,low,nit). Do not drop low or nit findings during collection. Severity or action filtering is a separate consumer stage after the collection record is complete (scripts/finding_pipeline.py). mediumfavors precision,xhighfavors recall. Atmedium(8 angles) assign severity carefully so a later filter can pick maintainer-action findings. Atxhigh(10 angles plus a gap sweep) a single non-REFUTED vote carries the finding; do not drop on uncertainty.- Every retained finding carries
severityandverdict. Severity is one ofblocker,high,medium,low,nit. Verdict isCONFIRMEDorPLAUSIBLE. Drop REFUTED candidates only; never emit an unclassified retained finding. --fixapplies findings once. Loadreference/fix.mdand follow it — it owns the fix agent, the code-rules gate, skip logging, and outcome reporting. Commits are lead-owned; fix agents never commit or push.loopnever asks. A round with bug findings validates them with an advisor, fixes, and re-reviews. Terminals are exactlyclean,nits_fixed, andadvisor_blocked. There is no reviewed-head count limit; a new head increments the count once, a re-review of the same head does not. Loadreference/loop.mdand follow it.--fixandloopcombine. With both, each loop round runs the level file, and the round's fixing happens insidereference/loop.md's gate sequence, which loadsreference/fix.mdfor the mechanics. There is no separate fix pass around the round.
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/effort-evaluation.md 1.4 KB
- reference/fix.md 3.8 KB
- reference/loop.md 14 KB
- reference/low.md 4.0 KB
- reference/medium.md 9.9 KB
- reference/mode-contract.test.mjs 2.6 KB runs code
- reference/preflight-proposal.md 1.3 KB
- reference/runner-selection.md 1.7 KB
- reference/xhigh.md 10 KB
- scripts/config/e_code_review_effort_constants/__init__.py 1.1 KB runs code
- scripts/config/e_code_review_effort_constants/effort_constants.py 1.3 KB runs code
- scripts/e_code_review_scripts_constants/__init__.py 51 B runs code
- scripts/e_code_review_scripts_constants/finding_pipeline_constants.py 1.7 KB runs code
- scripts/e_code_review_scripts_constants/grok_code_review_constants.py 1.4 KB runs code
- scripts/effort_defaults_evidence.json 5.2 KB
- scripts/effort_evaluation.py 13 KB runs code
- scripts/finding_pipeline.py 4.5 KB runs code
- scripts/fixtures/demanding.json 732 B
- scripts/fixtures/easy.json 406 B
- scripts/fixtures/medium.json 533 B
- scripts/grok_code_review.py 7.4 KB runs code
- scripts/test_effort_evaluation.py 6.8 KB runs code
- scripts/test_finding_pipeline.py 6.2 KB runs code
- scripts/test_grok_code_review.py 8.7 KB runs code
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 · 91 lines · 92 tokens per session scan A b050dc694549
e-code-review is a skill published in the GitHub repository jl-cmd/claude-dev-env (6 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 1,831 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…