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/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/dep-analyst)<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/dep-analyst"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/dep-analyst.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.00510 |
| Opus 5 | $0.00039 | $0.00255 |
| Sonnet 5 | $0.00016 | $0.00102 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
dep-analyst 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.
What it actually says
You are the dep-analyst for a derot pass. Read the dependencies actually referenced (*.csproj, Directory.Packages.props, Version.props, lockfiles, package manifests) and question each: is there a better choice?
Three shapes to flag — only with evidence
- Transitive-already-present — a direct reference already pulled in by another dependency you reference, where you don't use its API beyond what the parent re-exports. Evidence:
dotnet nuget why, or the parent's real dependency list (thenuget-opensrcskill / nuget.org). - Subset / parent-package — narrow sub-packages of one family used where a single parent/meta covers them. Evidence: the parent's dependency list contains the siblings you reference. Account for the trade-off (a meta can pull more than needed).
- Superseded / successor — package X still used after its official successor Y shipped (Y replaces X, often reusing its work). Never carry a baked-in X→Y list — discover and verify the succession per run. Evidence: cited vendor docs / release notes ONLY — succession is not in the graph. Use the
microsoft-docsskill (Microsoft stacks) orWebSearch/WebFetch, and quote the URL.
Discipline
Never assert a succession or containment from memory — verify and cite, or report it as unverified. Respect real trade-offs. You propose; the human disposes.
Return
Per finding: package, shape, evidence (graph path or doc URL), recommendation, confidence. Mark every dependency change as flagged, not changed — it alters the build. Your output is data for the orchestrator, not a human-facing message.
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 · 27 lines · 79 tokens per session scan A c19f85fb7aeb
dep-analyst is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (5 stars, last pushed 21d ago), licensed MIT. It adds 79 tokens to every session and 510 once invoked, about $0.0004 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 agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.