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 dcassil/resume-kit --skill seed-terminologygit clone --depth 1 https://github.com/dcassil/resume-kitWrote 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/dcassil/resume-kit/seed-terminology)<a href="https://agentmods.dev/skills/dcassil/resume-kit/seed-terminology"><img src="https://agentmods.dev/badge/skills/dcassil/resume-kit/seed-terminology/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/dcassil/resume-kit/seed-terminology"><img src="https://agentmods.dev/badge/skills/dcassil/resume-kit/seed-terminology.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 | $0.00203 | $0.01710 |
| Opus 5 | $0.00102 | $0.00855 |
| Sonnet 5 | $0.00041 | $0.00342 |
| Haiku 4.5 | $0.00020 | $0.00171 |
Grade A, and why
seed-terminology 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 8d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seed-terminology — auto-seed & grow the alias index (truth-gated)
Purpose
On a fresh project config.alias_file is None, so the deterministic matchers
(match / check-keywords / check-gaps / suggest-terminology) mirror only
the built-in seed lexicon. A resume that says responsive UI scores as missing
the JD's responsive design; monitoring misses observability; and
coverage is silently understated for pure phrasing differences the candidate
genuinely satisfies — with no flow step ever creating or growing the file.
This skill closes that gap. Run once a resume + job are both active and BEFORE the first keyword/gap check, it:
- Proposes conservative candidate pairs with the deterministic fuzzy
pre-filter (
suggest-terminology-candidates) — the one new capability. It only surfaces(jd_keyword, resume_phrase)pairs for missing JD keywords the resume plausibly satisfies under a near-miss surface form (shared stem + one differing token, or a small single-token edit distance). It proposes only;confirmedis always false. - Truth-gates + confirms each proposal through the learn-terminology loop (below). Nothing is written without an explicit user "yes".
- Seeds or grows the
alias_file: create + register on first run, append + dedupe on every later job — never overwrite, never drop prior entries.
It writes DATA only. Scoring stays deterministic and provider-free. Unconfirmed proposals never affect any score — the conservative-lexicon guarantee is preserved.
Run me in a subagent
Self-contained and file-mutating, like parse-resume / learn-terminology. The
main agent dispatches it a subagent with: the active resume + job JSON paths, the
path to resume-kit/config.json, and this skill. The subagent returns only what
it seeded/grew (canonical, alias, why) plus what it rejected/deferred — not the
full resume/job text.
Where the alias file lives
The path is config.json's alias_file. Read it; default to
resume-kit/learning/synonyms.json if the key is absent (the fresh-project
case). This is the SAME file the scoring skills pass to the engine, so growth and
scoring stay in lock-step. Format is the RIT-T-0068 shape documented in
learn-terminology ({version, aliases, justifications, provenance}).
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.
- 8d ago First seen · 124 lines · 203 tokens per session scan A b7bc99ec10f3
seed-terminology is a skill published in the GitHub repository dcassil/resume-kit (0 stars, last pushed 28d ago), licensed Apache-2.0. It adds 203 tokens to every session and 1,710 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…