Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add akougkas/wtf-p/plugin install wtfpWrote 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/check-refs)<a href="https://agentmods.dev/commands/akougkas/wtf-p/check-refs"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/check-refs/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/check-refs"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/check-refs.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 | $0.00021 | $0.00967 |
| Opus 5.5 | $0.00008 | $0.00387 |
| Sonnet 5.5 | $0.00004 | $0.00193 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
check-refs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
97% identical to wtfp:check-refs — 75 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check references
@${CLAUDE_PLUGIN_ROOT}/project/README.md @${CLAUDE_PLUGIN_ROOT}/skills/wtfp-research-literature/SKILL.md @${CLAUDE_PLUGIN_ROOT}/skills/wtfp-research-literature/references/actions.md
Record contract
Read: project://config, project://sources/{source}, project://evidence/{evidence}, project://materials/{artifact}, project://paper/{artifact}.
Produce: project://deliverables/bibliography/{artifact} (create), 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
- Resolve the author-selected bibliography, every in-scope manuscript citation, and verified or provisional source/evidence records under the configured citation policy.
- Report missing identities, metadata conflicts, uncited entries, unsupported citations, and style defects; search declared metadata providers for candidate records only after the gate names the providers and bounded query set. Treat provider results as candidate audit evidence until independently verified.
- Leave the bibliography, manuscript, source records, and evidence records unchanged. When requested, preview and create a separate corrected-bibliography candidate, validate it, and record unresolved issues and exact input revisions in the audit result.
Bundled tool execution
The declared tool.execute effect authorises exactly one command, run from the package root the host resolves for this bundle:
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 0e6b1a3c0d43
- 1mo ago Changed · +58 lines eeb296cb5352
- 1mo ago First seen · 17 lines · 21 tokens per session scan A 34b30783ec06
check-refs is a command published in the GitHub repository akougkas/wtf-p (20 stars, last pushed 19d ago), licensed MIT. It adds 21 tokens to every session and 967 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to wtfp:check-refs, differing in 75 lines, and is treated as a copy.
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.