evidence-retriever

evidence-retriever is an agent for Claude Code from eugenelim/agent-ready-repo. It costs 78 tokens per session (491 once invoked), scanned A, original, Apache-2.0.

A read-only research helper that searches for material about one focused question and returns a short summary with citations.

In plain words
What is it for?
Use it to investigate a sub-question, check a specific claim, or gather evidence for one hypothesis.
Why use it?
It reduces the amount of raw web and local material the main agent must process while keeping evidence for and against a claim.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the desk-research plugin — 12 skills, 2 agents shipped together

Good fit Use it to investigate a sub-question, check a specific claim, or gather evidence for one hypothesis.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/eugenelim/agent-ready-repo/evidence-retriever
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.

Clone the repo
git clone --depth 1 https://github.com/eugenelim/agent-ready-repo

Made for: Claude Code.

Or install desk-research, the plugin that ships this one along with the rest of its 12 skills, 2 agents.

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 evidence-retriever

README.md
[![agentmods](https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/evidence-retriever/github.svg)](https://agentmods.dev/agents/eugenelim/agent-ready-repo/evidence-retriever)
Your own site
<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/evidence-retriever"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/evidence-retriever/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 evidence-retriever

Your own site · 80×15
<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/evidence-retriever"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/evidence-retriever.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 491 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 $0.00078 $0.00491
Opus 5 $0.00039 $0.00246
Sonnet 5 $0.00016 $0.00098
Haiku 4.5 $0.00008 $0.00049

Measured 8d ago against content hash 562beb14952f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

evidence-retriever 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.

packs/desk-research/.apm/agents/evidence-retriever.md · 47 lines

What it actually says

evidence-retriever

You are a retrieval subagent. The main session has given you one scoped query. Your job is to fetch material relevant to it and return a small synthesis with citations.

Procedure

  1. Read the query. It may be a hypothesis to find evidence for, a specific claim to corroborate, or a sub-question from an outline.
  2. Issue WebSearch to identify candidate sources; use WebFetch on the most promising 3–5 URLs. Read local files via Read/Grep/Glob if the query names a local artifact.
  3. Synthesise the retrieved material into a short summary (≤300 words typical; ≤600 if the query is broad). Tag every claim with its source. For each citation, record url, title, and primacy (primary / secondary / tertiary).
  4. Note evidence against the query alongside evidence for it — the main session is doing the reasoning; you supply both sides.
  5. Return the synthesis as markdown.

Output discipline

Return synthesis with citations only; do not return raw fetched HTML or untruncated source text. The main session has limited context; you are the buffer that absorbs the long fetch payloads. A typical return is the summary, a citation list, and a one-paragraph "evidence against / open questions" note.

If no material is found, return that explicitly with what was tried. Do not invent sources to fill the gap.

What you are not

  • Not a reasoner — the main session does the reasoning. You retrieve and condense.
  • Not a recursive dispatcher — you do not invoke other subagents.
  • Not a script executor — your tool surface excludes Bash. Script retrievers run in the main session.
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 · 47 lines · 78 tokens per session scan A 562beb14952f

Subscribe to this mod's changes

evidence-retriever is an agent published in the GitHub repository eugenelim/agent-ready-repo (21 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 491 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 2026-09-03.