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 heidihelena/citevahti --skill citevahti-supportgit clone --depth 1 https://github.com/heidihelena/citevahtiWrote 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/heidihelena/citevahti/citevahti-support)<a href="https://agentmods.dev/skills/heidihelena/citevahti/citevahti-support"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-support/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/heidihelena/citevahti/citevahti-support"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-support.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 | $0.00068 | $0.01217 |
| Opus 5 | $0.00034 | $0.00609 |
| Sonnet 5 | $0.00014 | $0.00243 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
citevahti-support 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CiteVahti support — triage, known issues, escalation
CiteVahti runs in live pilots with real researchers; a support failure isn't an annoyed user — it's a damaged audit trail, or a manuscript submitted on bad information. This skill makes support responses consistent, honest, and correctly escalated.
Activation gate (from docs/BETA_TO_PRODUCTION.md): this workflow is mandatory
before the first paying customer — during free beta, apply it lightly rather than
building process for its own sake.
Triggers
Use when: a bug report, pilot feedback, support email, or GitHub issue arrives; drafting a reply; updating the known-issues register; deciding severity/escalation.
Do NOT use for: fixing the bug itself (normal development, gated by
secure-release when it ships), or feature requests (route to ROADMAP.md triage).
Escalation criteria — check these FIRST, before anything else
Two report classes are immediate, drop-everything escalations:
- Data loss — a user's ledger, audit log, ratings, manuscript edits, or Zotero library damaged or destroyed by CiteVahti. The audit chain is the product's promise.
- False-verified — CiteVahti recorded, displayed, or exported a support/decision
value the human did not make: an AI rating that leaked into
final_value, a decision shown as accepted that wasn't, an audit entry that misstates what happened. This is an invariant breach (docs/SAFETY_INVARIANTS.md), not a bug like the others.
For either: acknowledge within hours, not days; reproduce against the invariant tests
(test_dual_rating.py, test_readonly_tools_dont_mutate.py, the security marker
group); if confirmed, treat per SECURITY.md (a bypassed safety control is a security
issue even with no traditional vulnerability) — fix, add the regression test to the
security group, disclose honestly in CHANGELOG.md and to affected pilot users, and
consider whether shipped releases need a warning note. Never quietly patch an
invariant breach.
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 · 98 lines · 68 tokens per session scan A 2808a97fd1e0
citevahti-support is a skill published in the GitHub repository heidihelena/citevahti (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,217 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
diagnose
Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when the user says "why is my regression wrong", "this number changed", "my script errors out", "the result won't reproduce", "debug this", "this estimate…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
adjudicate-review
Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review comments, audit…
blast-radius
Before and after changing anything shared — a function's return value, a signature, a schema, a label set, a config default, a constant, a file format — find every consumer and actually run them. Catches the change that looks purely additive but silently breaks a contract in a file you never opened. Use when editing…