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.
git 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/commands/akougkas/wtf-p/wtfp-create-outline)<a href="https://agentmods.dev/commands/akougkas/wtf-p/wtfp-create-outline"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/wtfp-create-outline/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/commands/akougkas/wtf-p/wtfp-create-outline"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/wtfp-create-outline.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 | $0.00019 | $0.01058 |
| Opus 5 | $0.00010 | $0.00529 |
| Sonnet 5 | $0.00004 | $0.00212 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
wtfp:create-outline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create the paper outline
@${PLUGIN_ROOT}/project/README.md @${PLUGIN_ROOT}/skills/wtfp-start-project/SKILL.md @${PLUGIN_ROOT}/skills/wtfp-start-project/references/actions.md
Record contract
Read: project://manifest, project://config, project://state, project://decisions, project://structure/outline, project://sources/{source}, project://evidence/{evidence}.
Produce: project://structure/outline (update), project://sections/{section} (create), project://decisions (update), project://state (update), project://validations/{validation} (create).
Resolve every logical URI through the host adapter. Portable v1 JSON records are the source of truth: schema-validate before a write, preserve stable IDs, update revision and timestamps where required, and replace records atomically. Never pass a literal logical URI to a shell command or infer record state from a legacy Markdown control file.
Manuscript prose and supporting context, research, plan, review, summary, handoff, and deliverable artifacts retain their authored format (normally Markdown). Link them from the relevant v1 record; do not convert manuscript prose into project-state JSON.
Procedure
- Read existing outline, decision, and state revisions before deriving the thesis, requirements, locked/deferred decisions, source coverage, section goals, dependencies, word budgets, and execution waves.
- Reconcile only choices the author explicitly resolves during the outline interview. Preserve every unrelated decision unchanged. For each explicitly resolved item whose current disposition is
deferred, preserve the prior item unchanged except for setting its disposition tosuperseded; append a new replacement whose ID is fresh and unique in the ledger, whose authority isauthor, whose disposition islocked, and whosesupersedesfield names the prior item. Set the replacement'srecorded_atto the actual resolution time, increment the decision-record revision, and set the record'supdated_atto that same actual resolution time. Never supersede a locked choice or treat an agent suggestion or approval of an unrelated outline detail as authority to resolve a decision. If the author resolves no choice, do not rewrite the decision record. - Present the complete outline and decision diffs at the confirm_outline gate. If the proposed outline contradicts a locked decision, preserve that decision as locked and unchanged. If it assumes a choice that was already deferred and the author did not resolve it, preserve that choice as deferred. In either case, record a non-passing validation and stop before downstream planning.
- After approval, atomically publish the decision update when one is required together with the outline, one section record per entry, state update, and validation. Preserve stable record and section IDs and verify the complete approved set after writing.
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.
- 10d ago First seen · 75 lines · 19 tokens per session scan A bc788ccbf93f
wtfp:create-outline is a command published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 11d ago), licensed MIT. It adds 19 tokens to every session and 1,058 once invoked, about $0.0001 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 commands, from other repositories
retro
Reflect on the current research session and collect improvement suggestions.
setup_research_plan
Set up or start a research project.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.