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/fiberplane/claude-code-plugins/fp-reviewnpx skills add fiberplane/claude-code-plugins --skill fp-reviewgit clone --depth 1 https://github.com/fiberplane/claude-code-pluginsWhat 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 | $0.00052 | $0.02139 |
| Opus 5 | $0.00026 | $0.01069 |
| Sonnet 5 | $0.00010 | $0.00428 |
| Haiku 4.5 | $0.00005 | $0.00214 |
Grade C, and why
fp-review scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
> curl -fsSL https://setup.fp.dev/install.sh | sh -s Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> curl -fsSL https://setup.fp.dev/install.sh | sh -s How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FP Review Skill
Ensure commits are properly linked to issues and provide review feedback.
Prerequisites
Before using fp commands, check setup:
# Check if fp is installed
fp --version
If fp is not installed, tell the user:
The
fpCLI is not installed. Install it with:curl -fsSL https://setup.fp.dev/install.sh | sh -s
# Check if project is initialized
fp tree
If project is not initialized, ask the user if they want to initialize:
This project hasn't been initialized with fp. Would you like to initialize it?
If yes:
fp init
Core Purpose
- Verify commits are assigned to the correct issues
- Leave review comments on issues
- Open interactive review in the desktop app
- Create stories — narrative documents that walk through code changes
Assigning Commits to Issues
Check Current Assignments
fp issue files <PREFIX>-X
If empty, the issue has no commits assigned.
Find Relevant Commits
jj log --limit 20 # Jujutsu
git log --oneline -20 # Git
View Commit Details
jj show <commit-id> # Jujutsu
git show <hash> --stat # Git
Match Commits to Issues
Compare:
- Files changed in commit vs issue description
- Commit message content vs issue title
- Code changes vs issue requirements
Assign Commits
Before assigning commits, confirm with the user. Some users prefer to work without committing until they're done, or may not want commits linked to issues.
Use AskUserTool to ask:
I found these commits that appear related to
<PREFIX>-X:
abc123- Add user modeldef456- Implement auth middlewareWould you like me to assign them to the issue? (If you prefer to review uncommitted changes instead, you can run
fp reviewfor the working copy.)
If confirmed:
# Single commit
fp issue assign <PREFIX>-X --rev abc123
# Multiple commits
fp issue assign <PREFIX>-X --rev abc123,def456,ghi789
# Current HEAD
fp issue assign <PREFIX>-X
# Reset and reassign
fp issue assign <PREFIX>-X --reset
fp issue assign <PREFIX>-X --rev abc123,def456
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 · 365 lines · 52 tokens per session scan C b4c199b40fbc
fp-review is a skill published in the GitHub repository fiberplane/claude-code-plugins (40 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 2,139 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.