vigiles: Skill for Claude Code

.claude/skills/deep-research/SKILL.md

deep-research is a skill for Claude Code from zernie/vigiles. It costs 73 tokens per session (754 once invoked), scanned C, original, MIT.

A research workflow for gathering information from many sources or parallel investigations and saving both a summary and the detailed findings.

In plain words
What is it for?
Use it for in-depth topic research, competitor or market mapping, and investigations that need source details preserved on disk.
Why use it?
It prevents important research details from being lost when large amounts of information are compressed into a short answer or disappear with temporary agent work.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

This is zernie/vigiles's own configuration. It tells Claude Code how to work on vigiles itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vigiles configures →

Part of the vigiles plugin — 26 skills, 4 hooks, 2 plugins shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to zernie/vigiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zernie/vigiles/main/.claude/skills/deep-research/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zernie/vigiles

Made for: Claude Code.

Or install vigiles, the plugin that ships this one along with the rest of its 26 skills, 4 hooks, 2 plugins.

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 deep-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/zernie/vigiles/deep-research.svg)](https://agentmods.dev/skills/zernie/vigiles/deep-research)
Your own site
<a href="https://agentmods.dev/skills/zernie/vigiles/deep-research"><img src="https://agentmods.dev/badge/skills/zernie/vigiles/deep-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 754 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 25 Jun 2026
  • Snyk warn 25 Jun 2026
How audits are shown
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 $0.00073 $0.00754
Opus 5 $0.00036 $0.00377
Sonnet 5 $0.00015 $0.00151
Haiku 4.5 $0.00007 $0.00075

Measured 8d ago against content hash 5acec04cd62c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

deep-research scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- vigiles:ignore-test — project-local workflow skill, not a shipped vigiles surface -->
.claude/skills/deep-research/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep research — gather wide, lose nothing

The failure mode this skill exists to prevent: a big parallel research fan-out gathers 80–100K tokens of detail, each subagent returns a trimmed summary, the orchestrator compresses again into a short brief, and the raw findings live only in ephemeral agent transcripts (scratchpad task outputs) that vanish when the container is reclaimed. Net: expensive research → a thin artifact, detail gone. Don't do that.

The rule: two durable artifacts, never just one

Every nontrivial research effort produces, and SAVES to disk:

  1. A synthesis — the brief / answer (tables, thesis, recommendation).
  2. A full appendix — the per-source / per-company / per-angle DETAIL (raw numbers, funding histories, surfaces, dates, verbatim source URLs) the synthesis compressed.

If the saved synthesis is dramatically smaller than what was gathered, the appendix is how you reconcile that — the detail must land somewhere durable, not only in chat or a transcript. "I summarized it in chat" is not saved.

Running a fan-out

  1. Plan the angles — one subagent per distinct angle (company, source class, sub-question). Tell the user which model each runs on and why (the subagent-model-note rule).
  2. Mandate write-to-disk in the subagent prompt. Every research subagent must WRITE its full findings to a durable file (e.g. the session scratchpad dir, one file per angle) with sources verbatim, and return only a short pointer + the headline findings. Do NOT rely on the agent's returned summary as the record — it is trimmed by construction and its transcript is ephemeral.
  3. Capture sources verbatim — every claim carries [number] [source URL] [date] [reported vs estimate]. URLs are the first thing lost in compression; keep them.
  4. Synthesize from the files, not from memory — read back the written files to build the synthesis, so nothing silently drops.
  5. Save both artifacts before declaring done — commit/write the synthesis AND the appendix. Then it's saved.

Read the full file on GitHub · 58 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. 8d ago First seen · 58 lines · 73 tokens per session scan C 5acec04cd62c

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository zernie/vigiles (15 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 754 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.