dep-recon

dep-recon is a skill for Claude Code from lifeinchords/claude-code-skills. It costs 101 tokens per session (3,164 once invoked), scanned A, original, MIT.

A source-code check for answering whether a dependency really contains a named symbol, option, configuration key or behavior. It treats the dependency’s GitHub repository as the main evidence.

In plain words
What is it for?
Use it before researching whether a library supports a feature, when a feature was added, or whether an option was removed.
Why use it?
It helps avoid relying on outdated documentation, search results or guesses about fast-changing software libraries.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it before researching whether a library supports a feature, when a feature was added, or whether an option was removed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lifeinchords/claude-code-skills/dep-recon
Install

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.

Any agent
npx skills add lifeinchords/claude-code-skills --skill dep-recon
Clone the repo
git clone --depth 1 https://github.com/lifeinchords/claude-code-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for dep-recon

README.md
[![agentmods](https://agentmods.dev/badge/skills/lifeinchords/claude-code-skills/dep-recon/github.svg)](https://agentmods.dev/skills/lifeinchords/claude-code-skills/dep-recon)
Your own site
<a href="https://agentmods.dev/skills/lifeinchords/claude-code-skills/dep-recon"><img src="https://agentmods.dev/badge/skills/lifeinchords/claude-code-skills/dep-recon/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.

agentmods 80×15 button for dep-recon

Your own site · 80×15
<a href="https://agentmods.dev/skills/lifeinchords/claude-code-skills/dep-recon"><img src="https://agentmods.dev/badge/skills/lifeinchords/claude-code-skills/dep-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,164 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.03164
Opus 5 $0.00051 $0.01582
Sonnet 5 $0.00020 $0.00633
Haiku 4.5 $0.00010 $0.00316

Measured 10d ago against content hash 403eef9d3868, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dep-recon 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 10d 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.

.claude/skills/dep-recon/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dep Recon

Three-phase probe of a dependency's GitHub repo to answer existence + capability questions with actual source, not speculation. Runs BEFORE context7 + web search.

When to use

Any claim, assumption, or question about whether something exists or behaves a certain way in an external dep:

  • "Does <flag> exist in <tool>?"
  • "Is there a way to <x> in <lib>?"
  • "What version added <feature>?"
  • "Was <thing> removed from <dep>?"
  • "Does <lib> support <behavior>?"
  • Anytime training data may be stale for a fast-moving dep.
  • A config var lookup

The core rule

context7 + web results are derivatives + can be stale, summarized, or wrong. A gh search code hit in main settles the question. Only fall back to context7/web when all three GH passes return empty AND you've verified with qualifiers that empty really means empty.

Confidence gradient, highest to lowest:

A: Local clone of the dep's repo / local offline docs (no truncation, no rate limit, no network) B: gh search hits in the official GH repo C: WebFetch of the dep's official docs page D: context7 (MUST be corroborated: see Fallback) E: Web search / blog posts / Stack Overflow

Phase 0: Ask about local resources (before anything else)

Before any GH query, ASK the operator:

"Do you have a local clone of <owner>/<name>, offline docs, or a vendored copy I should read first? (path, or 'no')"

If yes: use Grep directly on that path: same term variants you'd run on GH, no truncation, no rate limits, instant. Grep is the primary verb here; Read only to open a specific file after a Grep hit. A local match supersedes everything downstream (but verify it reflects a current branch, not a stale fork).

Example Grep shape for the local path:

# Grep tool calls: pseudocode
Grep(pattern="skip_output", path="/abs/path/to/local/lefthook", output_mode="content", -n=true)
Grep(pattern="skipOutput",  path="/abs/path/to/local/lefthook", output_mode="content", -n=true)
Grep(pattern="skip-output", path="/abs/path/to/local/lefthook", output_mode="content", -n=true)

Read the full file on GitHub · 271 lines

Changes

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.

  1. 10d ago First seen · 271 lines · 101 tokens per session scan A 403eef9d3868

Subscribe to this mod's changes

dep-recon is a skill published in the GitHub repository lifeinchords/claude-code-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 3,164 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens