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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/projects"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/projects.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01477 |
| Opus 5.5 | $0.00024 | $0.00591 |
| Sonnet 5.5 | $0.00012 | $0.00295 |
| Haiku 4.5 | $0.00006 | $0.00148 |
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 1mo 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 — 147 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.
- 1mo ago Changed · +2 lines a498e840fc07
- 1mo 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 23d ago), licensed MIT. It adds 59 tokens to every session and 1,477 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
factory-mcp
Use the Warp Factory MCP to hand work to a software factory and collaborate with it — bundle local work and send it to the cloud, find factory tasks from a Slack thread / Linear ticket / description, and pull a task down to test or iterate locally and hand it back.
oz-notify-user
Send a progress notification to the user who triggered this Oz task (e.g., via Slack or Linear).
oz-finish-task
Report task completion or failure back to the Oz platform when done with a task.
task-workstream-grouping
Infer stable semantic workstreams for ungrouped Sutando task history and apply the validated assignments to the durable workstream sidecar. Use for internal task-workstream-grouping maintenance tasks, initial history backfills, and later batches of tasks that need cross-channel or cross-device workstream organization.
pending-questions
Ask the owner a decision you need, list what is waiting on him, close a question once he has answered, or run the reminder. Use when blocked on the owner's word, or asked "what are you waiting on me for?".
sutando-migrate
M1 Part 2 workspace migration — guided walkthrough that scans legacy state across sources A (repo-root), B (/.sutando/workspace/), C ($SUTANDOWORKSPACE env-override), surfaces collisions, gets owner greenlight, commits, verifies, and (if sutando-plus + sync configured) re-routes the vault .git via…