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 agentmods add skills/openhands/extensions/evidence-based-citationsnpx skills add OpenHands/extensions --skill evidence-based-citationsgit clone --depth 1 https://github.com/OpenHands/extensionsWhat 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 | $0.00047 | $0.00716 |
| Opus 5 | $0.00023 | $0.00358 |
| Sonnet 5 | $0.00009 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
evidence-based-citations 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 2d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants every field value or factual claim you produce in the current response to be backed by an official, verifiable source. Apply this skill to the response that triggered it; do not assume it stays active for the rest of the conversation unless the user clearly asks for it to.
Output format
For each field or claim, respond with exactly these four labeled lines:
- Field: the field name (or a short description of the claim)
- Value: the value you are assigning (or the claim itself)
- Quote: the exact verbatim text from the source that supports the value
- Source: the official URL where the quote can be found
When there are multiple fields, repeat the block once per field. Keep blocks separated by a blank line.
Source selection rules
- Prefer primary sources, in this order:
- Official product / project documentation
- Standards documents (RFCs, W3C specs, ISO standards)
- Official API references
- Source code in the project's own repository
- Accept secondary sources (blog posts, Stack Overflow, forum threads, news articles, third-party tutorials) only as a last resort, and clearly label them as such in Source.
- The Quote field must contain text that actually appears at the Source URL. Do not paraphrase inside the quote, and do not stitch together text from different parts of the page without making the cut explicit (e.g. with
…). - If you cannot find an official source for a value, say so explicitly:
- Source:
No official source found.Then either omit the value, mark it as unverified, or ask the user how to proceed. Never invent a quote or URL.
- Source:
When to fetch
- If you have a browser / fetch tool available, retrieve the source page and copy the quote directly from it before responding.
- If you do not have a fetch tool, always respond with
Source: No official source found.rather than citing URLs from memory. LLMs cannot reliably verify URL accuracy or quote fidelity without actually fetching the page, even when a URL feels familiar.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 60 lines · 47 tokens per session scan A ebd2645e8e36
evidence-based-citations is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 716 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…