evidence-curator

evidence-curator is an agent for Claude Code, OpenCode from iamironz/ai-config-bundle. It costs 19 tokens per session (83 once invoked), scanned A, original, MIT.

An internal evidence-curation agent that turns activity records, checkpoints, and stored notes into short summaries.

In plain words
What is it for?
Summarising tool activity, validation checkpoints, unresolved requirements, working notes, and evaluation results.
Why use it?
It reduces scattered evidence into a concise account of what has been checked, what remains unresolved, and what should be handed off.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit Summarising tool activity, validation checkpoints, unresolved requirements, working notes, and evaluation results.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/iamironz/ai-config-bundle/evidence-curator
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/iamironz/ai-config-bundle

Made for: Claude Code, OpenCode.

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-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamironz/ai-config-bundle/evidence-curator/github.svg)](https://agentmods.dev/agents/iamironz/ai-config-bundle/evidence-curator)
Your own site
<a href="https://agentmods.dev/agents/iamironz/ai-config-bundle/evidence-curator"><img src="https://agentmods.dev/badge/agents/iamironz/ai-config-bundle/evidence-curator/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-curator

Your own site · 80×15
<a href="https://agentmods.dev/agents/iamironz/ai-config-bundle/evidence-curator"><img src="https://agentmods.dev/badge/agents/iamironz/ai-config-bundle/evidence-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 83 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 $0.00019 $0.00083
Opus 5 $0.00010 $0.00042
Sonnet 5 $0.00004 $0.00017
Haiku 4.5 $0.00002 $0.00008

Measured 10d ago against content hash 346c2a275650, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

evidence-curator 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.

.opencode/agents/evidence-curator.md · 19 lines

What it actually says

You curate evidence from local-first artifacts.

Focus on:

  • recent tool traces,
  • unresolved and satisfied gates,
  • small working-memory files,
  • compact eval summaries.

Return only evidence-backed findings and keep the summary terse.

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 · 19 lines · 19 tokens per session scan A 346c2a275650

Subscribe to this mod's changes

evidence-curator is an agent published in the GitHub repository iamironz/ai-config-bundle (2 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 83 once invoked, about $0.0001 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 agents, from other repositories

nauro-planner

Use to plan a non-trivial change before any code is written. Classifies doctrine risk (GREEN/AMBER/RED) via Nauro, writes a structured plan, and drafts decision additions, updates, or supersedes for the direct-user Delivery parent. Returns a plan and never writes project truth or edits files.

Nauro-AI/nauro · 69 tokens

nauro-reviewer

Use to review a PR or diff. First pass looks for real bugs introduced in the change (boundary conditions, error handling, test weakening, caller mismatches); second pass audits against the PR template, Nauro decision references, and project conventions. Read-only. Flags actionable code issues and blocks on hard-rule…

Nauro-AI/nauro · 99 tokens

nauro-tech-lead

Use to set or maintain project direction. Reads Nauro decisions, session transcripts, and PR diffs; judges architectural choices against active doctrine; and drafts complete decision additions, updates, or supersedes for the direct-user Delivery parent. Never writes project truth.

Nauro-AI/nauro · 57 tokens

nauro-executor

Use to implement an exact approved plan. Has full source edit and test access. Runs lint and tests before declaring done. Commits locally, drafts the PR, and never pushes or opens it. Never writes project truth.

Nauro-AI/nauro · 49 tokens

clawteam-rnd-backend

Backend R&D task agent — layered abstraction, defensive coding, consistency-first data, built-in observability, evolvable design, perf/resource awareness; architecture layers, quality trade-offs, error taxonomy, distributed consistency patterns.

deepelementlab/jupyter-studio · 52 tokens

clawteam-rnd-frontend

Frontend R&D task agent — component model, declarative UI, data-driven flow, progressive enhancement, perf-first, a11y built-in; layered architecture, CSR/SSR/SSG/ISR, state taxonomy, RAIL-style optimization.

deepelementlab/jupyter-studio · 57 tokens