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/humanbean17/jrag/requesting-code-reviewnpx skills add HumanBean17/jrag --skill requesting-code-reviewgit clone --depth 1 https://github.com/HumanBean17/jragWhat 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 | $0.00022 | $0.00879 |
| Opus 5 | $0.00011 | $0.00439 |
| Sonnet 5 | $0.00004 | $0.00176 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
requesting-code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requesting Code Review
Fan out a team of code reviewer subagents — one per review scope — and run them in parallel. Each reviewer gets precisely crafted context for its scope, never your session's history. Splitting the review across focused reviewers catches more than a single pass, and isolating their context preserves your own for continued work.
Core principle: Review early, review often.
When to Request Review
Mandatory:
- After each task in subagent-driven development
- After completing major feature
- Before merge to main
Optional but valuable:
- When stuck (fresh perspective)
- Before refactoring (baseline check)
- After fixing complex bug
How to Request
1. Get git SHAs:
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)
2. Decide the scopes:
Look at the diff and decompose it into review scopes. You choose the breakdown — by subsystem, by concern, by file cluster, whatever fits this change. There is no fixed set of scopes; pick what this diff actually needs (one or several). The goal is a focused, non-overlapping slice per reviewer.
3. Fan out the review team:
Dispatch one general-purpose reviewer per scope, all in one response so they run in parallel. Each fills the per-reviewer template at code-reviewer.md.
Shared placeholders:
{DESCRIPTION}- Brief summary of what you built{PLAN_OR_REQUIREMENTS}- What it should do{BASE_SHA}- Starting commit{HEAD_SHA}- Ending commit
Per-reviewer placeholder:
{SCOPE}- The slice of the diff this reviewer owns (you decide)
4. Merge findings:
Collect every reviewer's output, dedupe overlapping issues, and rank by severity. The merged result is your review.
5. Act on feedback:
- Fix Critical issues immediately
- Fix Important issues before proceeding
- Note Minor issues for later
- Push back if reviewers are wrong (with reasoning)
Example
[Just completed Task 2: Add verification function — diff spans index logic, CLI, and tests]
You: Let me request code review before proceeding.
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[Decide scopes from the diff: index logic, CLI, tests]
[Dispatch one reviewer per scope, all in one response]
Reviewer A — SCOPE: index/repair logic and data integrity
Reviewer B — SCOPE: CLI flag handling and user-facing behavior
Reviewer C — SCOPE: test coverage and assertion quality
(shared) DESCRIPTION: Added verifyIndex() and repairIndex()
(shared) BASE_SHA: a7981ec HEAD_SHA: 3df7661
[Team returns in parallel, you merge]:
Strengths: Clean architecture, real tests
Issues (deduped, ranked):
Important: Missing progress indicators
Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed
You: [Fix progress indicators]
[Continue to Task 3]
What ships with it
1 file 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.
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 · 117 lines · 22 tokens per session scan A 55cef17f97b0
requesting-code-review is a skill published in the GitHub repository HumanBean17/jrag (9 stars, last pushed 7d ago), licensed MIT. It adds 22 tokens to every session and 879 once invoked, about $0.0001 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
develop
Run /develop to build a feature, UI or backend, from an approved design, a page, component, API, service, or data slice. If something load bearing is undecided and no spec records it, it stops and routes you to /architect; otherwise it reads the spec plus AGENTS.md, builds, and advances the scope.
sync
Run /sync as the last step after a change is complete, around merge, to keep durable knowledge current. Updates root and nested AGENTS.md, reconciles the scope from repo evidence, and flags specs the change made stale. Surgical edits only: it adds lines, and rewrites single lines it owns. Never a whole section, never…
test
Run /test to write a test suite for code you just built or changed, after implementing a feature, route, or fix. Targets uncommitted changes automatically, reads test preferences.json for your framework (asks and saves it if absent), and picks the right strategy per file: happy path, edge cases, error states…
document
Run /document pr | changelog | release-note | postmortem (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or specs.
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…