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-statusgit 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 | $0.00031 | $0.00387 |
| Opus 5 | $0.00015 | $0.00193 |
| Sonnet 5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
cv-status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/cv-status
Show the current résumé state at any time — reuses the same emitters as the SessionStart hook, so the output matches what loads at session start, then adds a content summary the hook doesn't print.
Steps
-
Set
CV_FORGE_ROOTto the plugin root (${CLAUDE_PLUGIN_ROOT}), matching the hook's environment. -
From the repo root, run each emitter and print its output:
for f in "${CLAUDE_PLUGIN_ROOT}"/lib/context/*; do bash "$f"; doneThe emitters cover: the active résumé (name, headline, template — from
cv/.active), a setup nudge when nothing is configured yet, and a PDF preflight warning (only when the opt-inCV_FORGE_PDFexport path is enabled). No network. -
If
resume.jsonexists, read it directly (Claude reads JSON natively — no Node) and report section counts, e.g.:resume.json: basics ✓ (name, email, summary) work: 2 entries · education: 1 entry · skills: 4 entries projects: 1 entry · publications: 1 entryOnly list sections that are present and non-empty; omit a section line entirely if it's missing or an empty array.
-
If neither
cv/.activenorresume.jsonexists, the setup-nudge emitter already told the user to run/cv-new— don't repeat it, just confirm there's nothing to summarize yet.
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 · 40 lines · 31 tokens per session scan A 4829a7698fa1
cv-status is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 387 once invoked, about $0.0002 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.