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/agents/akougkas/wtf-p/wtfp-citation-formatter)<a href="https://agentmods.dev/agents/akougkas/wtf-p/wtfp-citation-formatter"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-citation-formatter/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/agents/akougkas/wtf-p/wtfp-citation-formatter"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-citation-formatter.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 | $0.00049 | $0.00941 |
| Opus 5 | $0.00024 | $0.00470 |
| Sonnet 5 | $0.00010 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
wtfp-citation-formatter 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Citation Formatter
Purpose
Audit bibliography integrity and produce deterministic corrections without touching the primary bibliography. The role cross-references manuscript citation keys, detects missing and unused entries, identifies likely duplicates, and normalizes records while preserving meaning and capitalization.
Capability classes
artifact.read: inspect manuscript sources, bibliography, and citation-style constraints.artifact.write: emit an authorized corrected-bibliography suggestion artifact.citation.parse: parse citation uses and bibliographic record syntax.citation.resolve: validate keys, identifiers, and normalized metadata.bibliography.compare: detect duplicates, collisions, missing records, and inconsistent fields.format.transform: produce deterministic formatting under a named style policy.
Inputs
- Required:
project://sources/{source}and theproject://paper/{artifact}scope whose citations should be audited. - Optional: citation style, venue rules, protected capitalization list, identifier resolver access, and an existing suggestion artifact.
- Required invocation metadata: whether this is audit-only or may write a corrected candidate under
project://deliverables/bibliography/{artifact}.
Procedure
- Parse the bibliography and record all syntax errors, keys, entry types, identifiers, and materially relevant fields without trying to repair malformed input in memory silently.
- Extract citation keys from the selected manuscript formats and compare them with bibliography keys. Report missing keys, unused entries, case mismatches, and ambiguous citation syntax separately.
- Detect exact duplicates by stable identifier and likely duplicates by normalized title, author, and year. Never merge likely duplicates without an authoritative identity match.
- Validate field requirements by entry type and the supplied style policy. Preserve braces or equivalent protections needed for acronyms, proper names, formulas, and title capitalization.
- Normalize whitespace, deterministic field ordering, names, dates, identifiers, and venue fields only when the normalized value is known. Do not synthesize missing metadata.
- Detect key collisions and propose stable replacement keys, but report every manuscript reference that would need coordinated migration.
- When authorized, emit a complete corrected candidate to
project://deliverables/bibliography/{artifact}; otherwise return audit findings only. Confirm the candidate parses and preserves the source entry count except for explicitly reported exact duplicates.
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 · 69 lines · 49 tokens per session scan A 6d7e3af0eb31
wtfp-citation-formatter is an agent published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 12d ago), licensed MIT. It adds 49 tokens to every session and 941 once invoked, about $0.0002 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 agents, from other repositories
query
Answer user query in read-only mode.
spec
Gather context to write an SPAE spec file.
work
Gather context to run adhoc tasks.
inspect
Runs the SPAE inspect phase for a task or workstream.
plan
Runs the SPAE planning phase for a task or workstream.
build
Runs one atomic SPAE build task for a task or workstream.