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/howar31/magi-workflow/review-codenpx skills add howar31/magi-workflow --skill review-codegit clone --depth 1 https://github.com/howar31/magi-workflowWhat 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 | $0.00125 | $0.02744 |
| Opus 5 | $0.00063 | $0.01372 |
| Sonnet 5 | $0.00025 | $0.00549 |
| Haiku 4.5 | $0.00013 | $0.00274 |
Grade A, and why
review-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/magi:review-code — code review (MAGI by default)
You are the coordinator. Review the current uncommitted change set (or a specified diff) and produce a structured verdict. Default: multi-CLI MAGI. Fallback: single-reviewer subagent.
0. Preflight
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-}"
[[ -z "$PLUGIN_ROOT" ]] && PLUGIN_ROOT="$(cd "$(dirname "$BASH_SOURCE[0]")/../.." 2>/dev/null && pwd)"
USER_CONFIG="$HOME/.config/magi-workflow/config.json"
If config missing → tell user to run /magi:setup.
Confirm we are inside a git repo:
git rev-parse --git-dir >/dev/null 2>&1 || { echo "not a git repo"; exit 1; }
0.5. State preflight (auto-refuse if not allowed)
STATE_JSON=$(bash "$PLUGIN_ROOT/scripts/shared/detect-state.sh")
blocked=$(jq -r '.disallowed_skills["review-code"] // empty' <<<"$STATE_JSON")
if [[ -n "$blocked" ]]; then
reason=$(jq -r '.disallowed_skills["review-code"].reason' <<<"$STATE_JSON")
suggest=$(jq -r '.disallowed_skills["review-code"].suggest' <<<"$STATE_JSON")
echo "Cannot run /magi:review-code: $reason"
echo "Suggested: $suggest"
exit 1
fi
--force skips preflight. The most common refusal: no diff to review
(working tree clean and nothing staged) — make changes first.
1. Determine the diff scope
In priority order:
--diff <range>— explicit (e.g.HEAD~3..HEAD,main..HEAD,<file>...). Pass through to git.--staged— review only staged changes.- (no flag) — review unstaged + staged changes against HEAD.
- If working tree is clean, fall back to last commit (
HEAD~..HEAD) and warn the user.
- If working tree is clean, fall back to last commit (
Capture the diff:
git diff $diff_args > "$workdir/changes.diff"
git diff --stat $diff_args > "$workdir/changes.stat"
Show the user git diff --stat first so they confirm scope before tokens
get spent.
2. Branch on review mode
2a. Single-reviewer mode (--single)
Dispatch the magi-reviewer subagent. Build a brief:
You are dispatched to review this change set.
## Repo
<path>, branch <branch>, target <upstream-branch>
## Diff
<paste of changes.diff or --reference if too large>
## Files to read in full
- <path>
- <path>
## Project context
- TECHSTACK.md: <verbatim or summary>
- Conventions: CLAUDE.md / AGENTS.md (root)
## Sprint contract (if a sprint context exists)
<verbatim PLAN.md and/or SPEC.md from magi/<num>-<slug>/>
## Acceptance criteria (if applicable)
<from current sprint's SPEC.md if exists>
## Output protocol
Follow your standard structure: Verdict + 🔴 / 🟡 / 🟢 sections.
If a sprint contract was provided above, additionally output a
`## Drift from contract` section with A / B / C classes per your agent
spec.
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 · 336 lines · 125 tokens per session scan A 0c94d466eeed
review-code is a skill published in the GitHub repository howar31/magi-workflow (2 stars, last pushed 3d ago), licensed MIT. It adds 125 tokens to every session and 2,744 once invoked, about $0.0006 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
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
comfyui-node-registry
Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
performance-analysis
Measurement approaches, profiling patterns, bottleneck identification, and optimization guidance. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.