Borrowing it
Nothing to install: this file belongs to HelloThisWorld/open-mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HelloThisWorld/open-mind/main/.agents/skills/wikipedia-glossary/SKILL.mdgit clone --depth 1 https://github.com/HelloThisWorld/open-mindWrote 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/hellothisworld/open-mind/wikipedia-glossary)<a href="https://agentmods.dev/skills/hellothisworld/open-mind/wikipedia-glossary"><img src="https://agentmods.dev/badge/skills/hellothisworld/open-mind/wikipedia-glossary/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/hellothisworld/open-mind/wikipedia-glossary"><img src="https://agentmods.dev/badge/skills/hellothisworld/open-mind/wikipedia-glossary.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 | $0.00091 | $0.02287 |
| Opus 5.5 | $0.00036 | $0.00915 |
| Sonnet 5.5 | $0.00018 | $0.00457 |
| Haiku 4.5 | $0.00009 | $0.00229 |
Grade A, and why
wikipedia-glossary scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "{base}/glossary/enrich" -H "Content-Type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wikipedia glossary enrichment
Open Mind extracts glossary terms verbatim from a project's own authoritative sources and never fabricates them. This skill adds an authoritative standard definition for those terms from Wikipedia — kept strictly separate from, and never replacing, the in-project definition.
How enrichment runs (pipeline guarantee + this portable skill)
Open Mind now runs enrichment automatically as a deterministic pipeline step:
after a project is learned (and on every server start via a recovery reconciler),
the in-app engine (openmind/wikienrich.py) looks up un-attempted terms and writes
results — so enrichment is guaranteed without depending on an agent remembering
to act. Wikipedia egress is allowed but audited (every call is logged to
/netlog); only the enrichment path may egress, and only single glossary terms are
sent — never project source.
This skill is the portable, manual/agentic interface to the same capability:
run it to (re)enrich on demand, change the disambiguation context, pin a domain
acronym, or enrich from a runtime that isn't the Open Mind app (Codex,
open-claw, etc.). It writes back via POST /glossary/enrich; the in-app engine and
this script share the same conservative matching. Use it when you want manual
control or an override — the pipeline covers the automatic case.
Two honesty guarantees are enforced on the Open Mind side:
- No invented terms. A standard definition is only attached to a term the
project's own sources already surfaced. An unknown term is reported under
missing, never created. - Verbatim definition untouched. The in-project definition and its
file:lineprovenance are preserved; the Wikipedia text is a distinct field, labelled and footnoted in the UI ("Open Mind used its search skill to extract the above from Wikipedia and tidy it").
When to use
- The user asks to enrich / add standard / authoritative / Wikipedia definitions to a project's glossary, or runs this skill by name.
- Typically right after a project finishes learning (its terms are extracted) and the user wants richer definitions than the project's own sources provide.
What ships with it
1 file 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.
- 2mo ago First seen · 186 lines · 91 tokens per session scan A 6befd14645a7
wikipedia-glossary is a skill published in the GitHub repository HelloThisWorld/open-mind (1 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 2,287 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
wikipedia-glossary compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wikipedia-glossaryHelloThisWorld/open-mind | Skill | 1 | 3mo ago | MIT | A | 91 | Claude Code, Codex |
| codestory-groundingTheGreenCedar/CodeStory | Skill | 37 | 2d ago | Apache-2.0 | A | 52 | Claude Code, Codex |
| memtrace-firstsyncable-dev/memtrace-public | Skill | 511 | yesterday | none | A | 115 | Claude Code |
| memtrace-style-fingerprintsyncable-dev/memtrace-public | Skill | 511 | yesterday | none | A | 111 | Claude Code |
| memtrace-decision-memorysyncable-dev/memtrace-public | Skill | 511 | yesterday | none | A | 137 | Claude Code |
| memtrace-fleet-firstsyncable-dev/memtrace-public | Skill | 511 | yesterday | none | A | 144 | Claude Code |
| memtrace-incident-investigationsyncable-dev/memtrace-public | Skill | 511 | yesterday | none | A | 99 | Claude Code |