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 akougkas/wtf-p --skill wtfp-manage-projectgit clone --depth 1 https://github.com/akougkas/wtf-pWrote 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/akougkas/wtf-p/wtfp-manage-project)<a href="https://agentmods.dev/skills/akougkas/wtf-p/wtfp-manage-project"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-manage-project/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/akougkas/wtf-p/wtfp-manage-project"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-manage-project.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 | $0.00080 | $0.00569 |
| Opus 5 | $0.00040 | $0.00284 |
| Sonnet 5 | $0.00016 | $0.00114 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
wtfp-manage-project 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage a WTF-P Project
Keep project state honest, resumable, and useful for routing the next academic action.
Select the action
- Use
progressto reconcile artifacts and recommend the next step. - Use
pause-writingorresume-writingto create and consume a session handoff. - Use
checkpointto save, list, or restore named snapshots. - Use
settingsto inspect and edit project policy. - Use
add-todoorcheck-todosto capture and triage non-blocking work.
Read references/actions.md for the selected action before mutating project state.
Apply the state contract
- Treat schema-valid v1 records and verified authored artifacts as the source of truth. Reconcile
project://statewithproject://structure/outline, section records, linked plans, summaries, reviews, handoffs, manuscript artifacts, source/evidence records, validations, and checkpoints before reporting progress. - Keep durable state factual and concise: position, completed work, decisions, blockers, pending work, word counts, and exact next action.
- Preserve Markdown handoffs, validation records, and human-action checkpoints after every decision that must survive a new session.
- Show a proposed settings diff and validate its schema before writing it.
- Require explicit confirmation before restoring a snapshot or taking any destructive or version-control action.
- Do not contact a package registry, external service, or version-control remote merely to display local progress.
- Update multiple state artifacts only after their primary operation succeeds; avoid advertising work as complete prematurely.
- Report what changed, what remains pending, and the safest next action.
Keep operations reversible
- Save snapshot metadata and verify it can be read before declaring a checkpoint successful.
- Never discard an active handoff until the author has actually resumed or explicitly closed it.
- Resolve, waive, or expire completed checkpoints without deleting their audit history.
- Reject unknown configuration keys under the closed v1 schema; do not silently carry legacy settings into the portable record.
- Keep all paths relative to the project. Never embed client home directories or machine-specific state.
- Treat VCS operations as separate actions, never implicit project bookkeeping. A checkpoint restore remains an explicit gated state effect.
What ships with it
2 files 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.
- 11d ago First seen · 41 lines · 80 tokens per session scan A c27f9aac8599
wtfp-manage-project is a skill published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 12d ago), licensed MIT. It adds 80 tokens to every session and 569 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
ainb-fleet
Fleet orchestration overview — the ainb fleet ... Rust subcommand namespace for driving every claude session on the host. Routes to the sub-skills (ainb-spawn / standup / broadcast / sequence / needs / daemon / atc). Invoke this for an at-a-glance map of what fleet can do; reach for the specific sub-skill for the verb…
git-workflow
Branching strategies, conventional commits, PR templates, and merge vs rebase guidance. Activate when starting features, creating PRs, or managing releases.
ainb-fleet:fleet-needs
Workflow-backed Jarvis control panel. Runs the deterministic hangar workflow with verb=needs (discover → enrich → prioritize), renders the Jarvis HUD from its render-ready cards, fires AskUserQuestion per blocked session, and routes each answer back via tmux send-keys (broker fallback only). Requires the workflow gate…
batonq-pr-runner
Implements a batonq task end-to-end and opens a pull request. Adds git discipline, branch naming, conventional-commit enforcement, and PR-body conventions on top of batonq-worker. Use when a task explicitly requires a PR (not a direct commit to main) — e.g., tasks running in fire-and-forget mode against repos with…
batonq-worker
Default coding agent for tasks picked from a batonq queue. Karpathy-style discipline (think before coding, simplicity, surgical changes, verifiable goals) plus batonq-specific gates (verify and judge are mandatory; no skip flags). Use when implementing a normal task — fixing a bug, adding a feature, refactoring code.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…