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-review-section)<a href="https://agentmods.dev/commands/akougkas/wtf-p/wtfp-review-section"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/wtfp-review-section/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-review-section"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/wtfp-review-section.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 | $0.00023 | $0.00927 |
| Opus 5.5 | $0.00009 | $0.00371 |
| Sonnet 5.5 | $0.00005 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
wtfp:review-section scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a section
@${PLUGIN_ROOT}/project/README.md @${PLUGIN_ROOT}/skills/wtfp-review-manuscript/SKILL.md @${PLUGIN_ROOT}/skills/wtfp-review-manuscript/references/actions.md
Record contract
Read: project://manifest, project://decisions, project://structure/outline, project://sections/{section}, project://sections/{section}/context, project://sections/{section}/plans/{plan}, project://sections/{section}/research, project://sections/{section}/summary, project://evidence/{evidence}, project://paper/{artifact}.
Produce: project://sections/{section}/reviews/{review} (create), project://validations/{validation} (create), project://sections/{section} (update).
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
- Resolve one manuscript section, its outline claims, context, plan, research, summary, decisions, evidence, neighboring prose, and review rubric.
- Dispatch one read-only review of claim coverage, reasoning, evidence, citations, coherence, prose, and requirements. If the structured result is malformed, allow at most one corrective retry for result-contract compliance; never retry until a reviewer says pass, and do not retry warning-only or explicitly accepted debt.
- Write layer, confidence, location, impact, recommendation, and other rich detail in the Markdown review. Encode the read-only validation using only members allowed by the closed v1 schema; issue objects contain only severity, summary, and optional evidence, and the root never gains an
input_revisionsmember. Disputed findings go through a user gate; accepted warning debt remains anissues-foundresult and does not authorize manuscript edits. - Update only the section record to link the review. Review does not write project state, create a pause checkpoint or handoff, invoke pause implicitly, or invent a
pausedphase; leave lifecycle transitions to their owning actions.
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 e2aa95422eb9
- 1mo ago Changed 8ea4b59b6b32
- 1mo ago First seen · 69 lines · 23 tokens per session scan A 5e08fde6af9f
wtfp:review-section is a command published in the GitHub repository akougkas/wtf-p (20 stars, last pushed 19d ago), licensed MIT. It adds 23 tokens to every session and 927 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
retro
Reflect on the current research session and collect improvement suggestions.
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.