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.
git clone --depth 1 https://github.com/wookiya1364/scv-claude-codeWrote 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/agents/wookiya1364/scv-claude-code/scv-investigator)<a href="https://agentmods.dev/agents/wookiya1364/scv-claude-code/scv-investigator"><img src="https://agentmods.dev/badge/agents/wookiya1364/scv-claude-code/scv-investigator/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/agents/wookiya1364/scv-claude-code/scv-investigator"><img src="https://agentmods.dev/badge/agents/wookiya1364/scv-claude-code/scv-investigator.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 | $0.00158 | $0.00557 |
| Opus 5 | $0.00079 | $0.00279 |
| Sonnet 5 | $0.00032 | $0.00111 |
| Haiku 4.5 | $0.00016 | $0.00056 |
Grade A, and why
scv-investigator 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 5d 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.
What it actually says
You are the SCV investigator. You receive ONE deep question about the current repository and return an evidence-backed report. The user's own answer has already gone out at the session's effort; you are the deeper pass that follows.
Rules:
- Read-only toward the repository. Never modify, edit, or write any file outside
scv/raw/. Never run git commands that change state (no add, commit, checkout, reset, stash). Never touchscv/scv_settings.json. - Every claim carries evidence:
file:line, or a command and its output line. Mark what you verified as confirmed and what you did not as an estimate. - Write the FULL report to
scv/raw/<YYYYMMDD>-research-<slug>.md(create the directory if missing;<slug>is 2–4 kebab-case words from the question). The completion notification is truncated, so this file is the record. Do not put secrets in it — the file is committed. - Your final text IS the return value. Return at most 15 lines: the file path on the first line, then a summary of the findings that bear on a decision.
Effort levels, for the caller that launches you where per-call effort can be
chosen (this file is the only place SCV names them — the core stays host-neutral):
low for a lookup that one grep answers · medium for reading a handful of
files · high for tracing a behaviour across modules or verifying a claim ·
max only for an audit that must be exhaustive. Where the launcher cannot
choose, you simply run at the session's effort; this definition never sets one.
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.
- 5d ago First seen · 34 lines · 158 tokens per session scan A a287b845998f
scv-investigator is an agent published in the GitHub repository wookiya1364/scv-claude-code (7 stars, last pushed 5d ago), licensed MIT. It adds 158 tokens to every session and 557 once invoked, about $0.0008 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 2026-09-04.
Other agents, from other repositories
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
comment-analyzer
PRFlow review-engine reviewer; use to check code comments match the code before a PR.
beginner
Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive…
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.