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 skills add 1020911401/ArchNavMCPServer --skill archnavgit clone --depth 1 https://github.com/1020911401/ArchNavMCPServerWrote 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/skills/1020911401/archnavmcpserver/archnav)<a href="https://agentmods.dev/skills/1020911401/archnavmcpserver/archnav"><img src="https://agentmods.dev/badge/skills/1020911401/archnavmcpserver/archnav/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/skills/1020911401/archnavmcpserver/archnav"><img src="https://agentmods.dev/badge/skills/1020911401/archnavmcpserver/archnav.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 | $0.00049 | $0.01294 |
| Opus 5.5 | $0.00020 | $0.00518 |
| Sonnet 5.5 | $0.00010 | $0.00259 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
archnav 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ArchNav (playbook)
v1.6.0 — 拆成「薄技能 + MCP prompts/resources + references」：正文只留触发条件与三个必知坑；四套工作流进 MCP
prompts，长文进resources（同一批文件）。完整旧版手册保留在references/playbook-full.md。 v1.5.0 — 新增archnav version <dir>（目标仓版本：git HEAD/branch/tag/dirty、manifest 版本、索引建于哪个 commit）。 v1.4.0 — 自审流程与六类假阳性、降噪四项（自审 25 → brief 模式 1 条）。
ArchNav 是给 agent 用的代码导航 + 评审层：图谱只负责带路（文件/行号），改代码前必须 read 真源码。
When to Use
- 在不熟悉的仓里定位符号、看分层 →
locate/read/arch/whereami - 评审一个 diff、算爆炸半径 →
changes/impact - 想知道这次改动该跑哪些单测 →
scripts/test-select.mjs - 仓库级深查（流程/聚类/风险/多仓接口）→
scripts/deep.mjs - 「我看的是哪一版代码」→
archnav version <dir>（git HEAD/branch/tag/dirty + 清单版本 + 索引建于哪个 commit）
三个必须先知道的坑
- 未跟踪文件不进 diff：审未提交的改动前先
git add -N .，否则新建文件根本不在git diff里。 - 先
analyze再审：索引过期会把新文件全报成「import 解析不到」（candidates tried=7）——拿旧索引的结论当证据等于审了个旧仓。 --json默认是压缩摘要（没有 message/evidence）：逐条 triage 必须--json --no-compact。- 索引口径决定一切：
analyze现在会读仓根.gitignore（{gitignore:false}/--no-gitignore可关）， 但只认子集（去掉首尾/、跳过!否定行）。没写进.gitignore的构建产物（如 Laravel 的storage/framework/views/、编译后的 Blade 缓存）仍会被索引——那些文件里的> ''、foreach+->where(会整片变成假阳。索引前先确认ignore字段是否覆盖了 vendor/构建目录；实测一个 Laravel 仓：不忽略 vendor 是 129 MB / 5m22s，忽略后 2.7 MB / 15s。 - 作用域调用（
$this->/self::/parent::）不再按裸方法名跨文件解析：解析不到会进knowledgeGraph.unresolvedScopedCalls（上限 200 条）+scopedCallStats。看到parent::大量 unresolved 是正常的（框架父类不在索引里），不要当成缺陷；反过来，如果某个$this->m()解析到了 别的文件，那是 bug 而不是证据。
MCP 侧（本仓 src/mcp-server.js）
装了 MCP 的客户端（Hermes / Claude Code / Cursor）可以直接拉：
| prompts（工作流） | resources（长文） |
|---|---|
archnav_review_diff 评审当前 diff |
archnav://skill 本页 |
archnav_self_review 审自己未提交的改动 |
archnav://skill/code-review 规则清单与真值 |
archnav_test_select 只跑相关单测 |
archnav://skill/self-review 假阳性/降噪清单 |
archnav_deep 仓库级深查 |
archnav://skill/comparison 三方跑分（证据，非依赖） |
archnav://skill/kanban-review 看板逐项确认 + 豁免回流 |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- prompts/deep.md 668 B
- prompts/review-diff.md 1.0 KB
- prompts/self-review.md 853 B
- prompts/test-select.md 658 B
- references/anchor-review.md 3.4 KB
- references/code-review.md 17 KB
- references/comparison.md 19 KB
- references/kanban-review.md 5.1 KB
- references/playbook-full.md 25 KB
- references/self-review.md 7.4 KB
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 Changed · +9 lines 2a3f515251d7
- 7d ago First seen · 54 lines · 49 tokens per session scan A 735500ca868d
archnav is a skill published in the GitHub repository 1020911401/ArchNavMCPServer (1 stars, last pushed 5d ago), licensed MIT. It adds 49 tokens to every session and 1,294 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-23.
Other skills, from other repositories
test-review
You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.
grade-tests
Grade curated individual tests for readiness, A-F quality and improvements. ALWAYS USE FOR: grade tests, review only a named test, per-test readiness or quality bands for supplied methods, bodies, file spans or bounded PR diffs, including existing tests. Return Pass/Failed/Uncertain/Not applicable; unresolved/empty…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
dart-mechanical-refactor
DART Mechanical Refactor: perform a behavior-preserving mechanical refactor.
refactor
Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.