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 commands/localplugins/plugins/cv-newgit clone --depth 1 https://github.com/localplugins/pluginsWhat 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 | $0.00028 | $0.00895 |
| Opus 5 | $0.00014 | $0.00447 |
| Sonnet 5 | $0.00006 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
cv-new 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cv-new
Create the single source of truth for every render: resume.json, validated
against ${CLAUDE_PLUGIN_ROOT}/schema/json-resume.schema.json. Zero-permission unless the user asks
to import from a URL (that one step is opt-in network use).
Steps
-
Check for an existing
resume.json. If one is already present, confirm the user wants to replace it (multi-résumé management viaresumes/<slug>/is Plan 2 — not built here; today there is one active résumé at a time). -
Pick a path: import or Q&A.
- Import. The user pastes an existing résumé (plain text, Markdown, or a copy-pasted PDF dump), or points at a local file path. Read the material directly and extract it into the JSON Resume shape below — Claude reads text and JSON natively, so no Node or external parser is needed. If the user instead gives a URL, that is the one opt-in network step: confirm with the user before fetching, then extract from the fetched page the same way. If a source is unreadable (e.g. a scanned/image-only PDF), fall back to Q&A for the fields that couldn't be recovered — never invent facts.
- Guided Q&A. Ask for, in order:
basics(name — required, label, email, phone, url, one-paragraph summary, location city/region), thenwork(name, position, startDate, endDate, one-line summary, 2–4 highlight bullets — repeat per job, most recent first),education(institution, area, studyType, startDate, endDate),skills(name + keywords, grouped into a few categories), and optionallyprojectsandpublications. Skip any section the user has nothing for — empty arrays are fine, the renderer omits empty sections automatically.
-
Assemble
resume.jsonmatching the JSON Resume subset in${CLAUDE_PLUGIN_ROOT}/schema/json-resume.schema.json(basics,work,education,skills,projects,publications). Use ISOYYYY-MMdates where known. -
Validate against the schema. Read
${CLAUDE_PLUGIN_ROOT}/schema/json-resume.schema.jsonand check the drafted JSON against it directly (Claude reads JSON natively — no Node, no library call):basicsis required andbasics.namemust be a non-empty string.basics.email, if present, must look like an email (.+@.+\..+).- every
work[]entry needsnameandposition. - every
education[]entry needsinstitution. - every
skills[]entry needsname.
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 · 72 lines · 28 tokens per session scan A 540c39b64af8
cv-new is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 895 once invoked, about $0.0001 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 commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
sprint
Sprint lifecycle — plan a sprint, run a retrospective, or generate release notes.
analyze-test
Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.