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/thewolffish/wolffish-app/projectsnpx skills add thewolffish/wolffish-app --skill projectsgit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thewolffish/wolffish-app/projects)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/projects"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/projects.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00059 | $0.01465 |
| Opus 5 | $0.00030 | $0.00732 |
| Sonnet 5 | $0.00012 | $0.00293 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
projects 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 6d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Projects — shared bases for conversations
You own this. Reach for it by intent whenever a need or issue touches a
project, its shared instructions, or its files — even if the user never names
it. The project_* tools are the way to manage projects; read the filesystem
only when a path genuinely isn't a project attachment.
A project bundles instructions plus a referenced file list; every fresh conversation started inside it gets that base as context (instructions verbatim, files as a model-led reference list — content is read on demand with pdf/file/image tools, never injected).
Interface
- Tools:
project_list,project_view,project_create,project_update,project_add_files,project_remove_file,project_delete,project_conversations - Identify a project by its 1-based number from
project_list, its exact title, or its id. - These tools operate on the same store as the app's Projects page — changes show there and apply to project conversations from their next turn.
Rules
- If the current conversation runs inside a project, the system prompt's
<project>block names it — that is "this project" when the user says so. - "What did we discuss in this project?" →
project_conversations, thenconversation_readon the relevant id. Never guess from memory when the transcript is one call away. - Before editing instructions,
project_viewfirst and modify from the CURRENT text —project_updatereplaces the whole instructions body, and a blind write erases the user's wording. - When attaching files the user mentioned loosely ("add my thesis"), resolve the real path
first (search the disk with your tools);
project_add_filesrefuses paths that don't exist. - Attaching COPIES the file into the project's workspace folder — the project owns its copy, so later edits to the user's original are NOT reflected; re-attach to refresh a stale copy.
- A project can also carry WORKING FOLDERS (
project_viewshows them). Those are references, not copies: every turn inside the project gets a FRESH listing of each one, so the folder is seen as it is right now. Do the project's file work in them, and treat paths the user mentions as relative to them unless they say otherwise. They are attached in the app. - Deleting is destructive and approval-gated; conversations survive a delete but lose the project context going forward.
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.
- 6d ago First seen · 145 lines · 59 tokens per session scan A 9f7966b49304
projects is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,465 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 2026-08-31.
Other skills, from other repositories
agent-computer-use
REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the agent-cu CLI commands (open, snapshot, click, type, key…
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
gui-integration-test
GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…
gui-onboarding-verification-skill
GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…
logging-and-error-reporting
How and when to log (log:: levels, safe macros) and report errors to Sentry (reporterror!) in the Warp codebase. Use when adding or reviewing any logging or error reporting — picking a log level, deciding log vs. reporterror!, keeping sensitive data out of logs, or surfacing an error to Sentry.