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-usegit 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 | $0.00017 | $0.00368 |
| Opus 5 | $0.00009 | $0.00184 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
cv-use scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/cv-use
Switch the active template for the current résumé.
Steps
-
List templates. Enumerate the directories under
"${CLAUDE_PLUGIN_ROOT}/templates/", excluding_shared(that one holds the renderer, not a template —render-core.js). Each remaining directory name is a template slug; each must contain atemplate.html. In Plan 1 that's justclassic-ats— the fuller gallery (modern,minimal,academic) and a rendered preview (output/gallery.html) arrive in Plan 2. Show the current active slug (line 1 ofcv/.active, if present). -
If a slug was given, verify it matches one of the listed template directories. If not, list the valid slugs and stop without changing anything.
-
If no
cv/.activeexists yet, tell the user to run/cv-newfirst (it creates the résumé and sets the initial template) and stop. -
Set active. Rewrite only line 1 of
cv/.activeto the new slug, preserving lines 2 (display name) and 3 (headline) exactly as they were. -
Re-render. Run
/cv-makeso the output file reflects the newly selected template.
Note: this switches the template for the one active résumé. Managing several
résumés side by side (resumes/<slug>/) is Plan 2, not built here.
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 · 36 lines · 17 tokens per session scan A 4fc173be478e
cv-use is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 368 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.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
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.