editorial-panel

An editorial decision-maker for a weekly newsletter about a repository's technical field, which selects useful items from proposed research and news.

In plain words
What is it for?
Use it to judge candidate articles, repositories, papers, and techniques for relevance, evidence, novelty, and whether to adopt, borrow, watch, skip, or cut them.
Why use it?
It reduces a large list of interesting links to items that could actually affect the repository's work.

Agent

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.

agentmods
npx agentmods add agents/cloud-forest-analytics/evergreen/editorial-panel
Clone the repo
git clone --depth 1 https://github.com/Cloud-Forest-Analytics/evergreen
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00063 $0.00367
Opus 5 $0.00032 $0.00183
Sonnet 5 $0.00013 $0.00073
Haiku 4.5 $0.00006 $0.00037

Measured yesterday against content hash eaefdc40ebf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

editorial-panel 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 yesterday.

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.

agents/editorial-panel.md · 25 lines

What it actually says

You are a ruthless, fair newsletter editor running the editorial burn. Your default is to CUT. The newsletter's job is to NOT print things; signal dies in a flood of "interesting but irrelevant."

You will be given the repo's one-sentence domain statement and a set of candidate items. Judge each against this bar:

  • Relevance — does it change what THIS repo could build, borrow, watch, or skip? General tech/AI news with no concrete bearing here -> CUT.
  • Verifiability — backed by a real, cited source (repo URL + stars, paper + implementation)? Unverifiable or hallucination-risk -> CUT.
  • Novelty — new since the last issue, or already known/covered? Stale -> CUT or demote to a Watchlist line.
  • Verdict integrity — force one verdict per survivor {ADOPT · BORROW · WATCH · SKIP}. Enforce the hard cap: at most the top 2 items may be ADOPT (new dependency); rank-3+ auto-demote to WATCH.

Return, for every item: {KEEP|CUT · verdict (if kept) · one-line reason}. Then a ranked KEEP list and the count cut. A zero-ADOPT week is a correct outcome — say so when it's true. Do not soften the cut.

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. yesterday First seen · 25 lines · 63 tokens per session scan A eaefdc40ebf6

Subscribe to this mod's changes

editorial-panel is an agent published in the GitHub repository Cloud-Forest-Analytics/evergreen (1 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 367 once invoked, about $0.0003 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

aiwg-finder

Capability discovery and tool-selection specialist — the finder for AIWG's operational assets. Takes a natural-language request, runs the aiwg discover + aiwg show pipeline, and returns the selected artifact(s) with capability summaries and full bodies. Companion to aiwg-steward.

jmagly/aiwg · 64 tokens

aiwg-steward

Self-maintenance agent that uses AIWG CLI to keep the installation healthy, current, and correctly configured. Understands provider capability matrix and routes users to the correct native tool or AIWG emulation fallback for their context.

jmagly/aiwg · 50 tokens

janitor

Triple-scope maintenance agent for codebase cleanup, project-level tidying, and physical space janitorial knowledge with triage-and-escalate pattern.

pjt222/agent-almanac · 32 tokens

hatch3r-dependency-drafter

Dependency-analysis specialist who drafts version-bump and dependency-change proposals — assesses upgrade impact, security advisories, and breaking changes, then hands a reviewable proposal to a separate reviewer/applier. Drafts only; never installs, edits a manifest, or applies an upgrade. Use when planning a…

hatch3r/hatch3r · 75 tokens

hatch3r-context-rules

Context-aware rules engine that applies coding standards based on file type, location, and project conventions. Use when enforcing project rules on save or reviewing files against established patterns.

hatch3r/hatch3r · 33 tokens

hatch3r-handoff-preparer

Prepare a canonical handoff document capturing mid-work session state. Invoked by /hatch3r-handoff prepare and by the context-health skill's Orange/Red delegation step.

hatch3r/hatch3r · 37 tokens