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 wahidyankf/ose-public --skill repo-understanding-shared-vocabularygit clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/repo-understanding-shared-vocabulary)<a href="https://agentmods.dev/skills/wahidyankf/ose-public/repo-understanding-shared-vocabulary"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/repo-understanding-shared-vocabulary/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/wahidyankf/ose-public/repo-understanding-shared-vocabulary"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/repo-understanding-shared-vocabulary.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 | $0.00066 | $0.00718 |
| Opus 5.5 | $0.00026 | $0.00287 |
| Sonnet 5.5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
repo-understanding-shared-vocabulary 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared Repository Vocabulary
Delegated agents do not inherit the canonical instruction file, so this Skill is how the shared vocabulary reaches them. It carries operative meanings only; where it and the glossary differ, the glossary wins.
Most scope disputes are vocabulary disputes in disguise: two readers who disagree about whether a rule applies usually agree on the rule and disagree on one word in it.
The terms
- Repo rules — every surface that binds how work happens, wherever it sits. Not a synonym for one directory: governance prose, the root instruction surfaces, agent and skill definitions, generated mirrors, the config's machine-readable declarations, the hooks and pipeline jobs enforcing them, and the language style guides. A sweep scoped to one tree skips most of it. The test for anything unlisted: editing it changes what someone is required to do, and that requirement outlives the work that prompted it. Declarations bind; the code enforcing them is an application, reviewed as product code. See Repo Rules — Scope Boundaries and Membership Test.
- Content trees — four trees differing by who is bound and for how long, not by subject: one describes the product, one binds contributors, one holds work that expires, one holds acceptance criteria. See Content Trees.
- Delivery unit — the unit a branch and a PR map to: a contiguous run of phases that ships on its own. A phase is smaller, and mapping a PR to a phase is the common error. See Plan Vocabulary.
- Surface and binding — a surface is the file class a gate measures; a binding is the harness-specific configuration, one hand-authored and the rest generated. "Autoloaded" is narrow — a link inside an autoloaded file is not itself autoloaded. See Governance Surfaces.
- Agent, skill, gate, workflow — distinguished by what holds the knowledge and who decides when it runs. See Agent Vocabulary.
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.
- 2d ago First seen · 51 lines · 66 tokens per session scan A ed91543bac60
repo-understanding-shared-vocabulary is a skill published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 718 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
implement
Implement an agreed issue or spec through implementation, review, fixes, and a PR ready to merge.
triage
Classify an issue, identify missing information, and decide whether bounded automatic work is safe.
record-gotchas
Capture surprises, workarounds, and rough edges hit while consuming the public surface of Prisma 8, Prisma Compute, or Prisma Postgres — anything a real user of these products would experience. Fires whenever an operator (or agent) writes a workaround, hits a surprising failure mode, or finds undocumented behaviour…
resolution_playbook
How to choose one resolution action from a ticket and its customer history.
stacking-prs
Create and manage GitHub native Stacked PRs in this repo with the gh stack CLI. Use when asked to stack PRs, split a large change into a stack, add a layer to a stack, restack or rebase a stack, adopt existing branches or PRs into a stack, check out someone else's stack, or land a stack. Covers creating and submitting…