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/hellothisworld/open-mind/glossarynpx skills add HelloThisWorld/open-mind --skill glossarygit clone --depth 1 https://github.com/HelloThisWorld/open-mindWhat 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 | $0.00050 | $0.00585 |
| Opus 5 | $0.00025 | $0.00293 |
| Sonnet 5 | $0.00010 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
glossary 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 yesterday.
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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glossary — deterministic, source-traceable term index
What it does
Scans a repository's authoritative sources (a dedicated GLOSSARY/acronym file, a
definition table or TERM: … line, a README/docs sentence, a doc-comment) and builds
a persisted map: term → {definition (verbatim), source_file, line_number, content_hash, source_kind}. A lookup resolves a term by exact token (no
similarity, no paraphrase) and returns the original text with a jump-to-source link,
or found: false for an absent term.
Determinism & anti-fabrication contract
- The definition is the exact original text lifted from the source — never reworded, summarized, or model-generated.
- Provenance is mandatory:
source_file:line_number+ acontent_hashof the source. - An unknown term returns
{found: false, message: "no authoritative definition found …"}. It is never guessed. - Incremental + idempotent: a per-file content hash means an unchanged source is reused, not re-parsed; same input → same output.
Grounded usage profile (value density)
On a single-term hit the entry carries a usage profile derived from the structure
map (openmind.structure.term_usage), all traceable to real code:
defined_at— definition site(s)file:line:kindwhen the term is also a code symbol;used_in/use_count— every file that references the symbol;modules— the modules the term spans;related_terms— other glossary terms co-located in the same files. For a pure concept/acronym (not a code symbol) the code lists are honestly empty; the module and related terms still ground it.
Invocation
- MCP tool:
get_glossary(scope, term=None)— withterm, the resolved entry; without, the full term list. - REST:
GET /glossary?scope=<project>&term=<term>(the entry, withusage). - Jump to source:
GET /source?scope=&file=&line=(allow-listed to indexed sources).
Implementation / tests
openmind/glossary.py (extraction + lookup), openmind/structure.py::term_usage
(usage profile). Acceptance: tests/verify_glossary.py.
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.
- yesterday First seen · 44 lines · 50 tokens per session scan A 62043a14b914
glossary is a skill published in the GitHub repository HelloThisWorld/open-mind (1 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 585 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
codestory-grounding
Use when an agent should ground a local repository with CodeStory before making source claims, planning edits, choosing tests, reviewing changes, or using broad retrieval evidence through the CodeStory plugin MCP.
memtrace-first
Route code discovery, debugging, flow tracing, how-code-works questions, and pre-edit rationale checks in indexed source-code repos to Memtrace graph plus Cortex decision tools. Use first before searching/reading code, and before editing, refactoring, deleting, or re-picking an approach that may have a recorded…
memtrace-style-fingerprint
Pull the codebase's empirical style norm from Memtrace and match it when writing or editing source code in an indexed repo. Use when choosing between competing idioms (ternary vs if-else, arrow vs function declaration, const vs let, await vs .then, early-return vs nested-return), matching naming case, or when the user…
memtrace-decision-memory
Use Cortex decision memory through the normal Memtrace MCP tools. Trigger for free-text questions about what was decided, chosen, rejected, banned, or established as a convention; for why a symbol exists or which contracts constrain it; for whether a known decision held, drifted, or was violated; and for the…
memtrace-fleet-first
Coordinate fleets of coding agents sharing one repo+branch: publish typed intents, classify edit episodes, and resolve conflicts before they collide. Use FIRST when multiple agents work the same repo+branch, before reading/planning/editing, when joining a fleet or handing work off, and when the user says two agents…
memtrace-change-impact-analysis
Compute what a planned source-code change will break — blast radius, affected processes, cross-repo callers, temporal stability, and Cortex decision-memory constraints — and produce a risk-rated change plan. Use for multi-symbol or multi-part edits, refactors, API changes, renames, removals, PR reviews, or risk…