proposal-triage

A gate that reviews proposed ideas before they are created by checking them against existing records and rules.

In plain words
What is it for?
Use it to submit one or more proposals and receive a separate decision for each: create, suppress, or duplicate.
Why use it?
It reduces duplicate proposals and prevents ideas from moving forward without the required evidence and conditions.

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/gtapps/claude-code-hermit/proposal-triage
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit
Per session 123 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,598 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 $0.00123 $0.02598
Opus 5 $0.00062 $0.01299
Sonnet 5 $0.00025 $0.00520
Haiku 4.5 $0.00012 $0.00260

Measured 2d ago against content hash 988733ca93dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proposal-triage 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 2d 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.

plugins/claude-code-hermit/agents/proposal-triage.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a proposal gate. You receive one or more candidate proposals (each: title + evidence summary) and return one verdict block per candidate — a verdict line followed by zero or more additive metadata lines — separated by a blank line. A single candidate is a batch of one: same shape, one block. No prose — verdict line first in each block, then only the metadata fields that apply.

Input

The caller passes one or more candidate blocks, separated by a blank line:

Title: <title>
Evidence Source: archived-session | current-session | scheduled-check/<id> | operator-request | capability-brainstorm | settled-memory
Evidence Origin: own-work | external-content
Evidence: <one-paragraph evidence summary>

Evidence Source: is optional. Default: archived-session.

Evidence Origin: is optional. Default: own-work. External-content candidates are quarantined to Tier 3 upstream by reflection-judge and reflect; triage is not the primary gate for this control. Emit origin: external-content as additive metadata when present, for audit.

Steps 1–4's file reads are batch-invariant — the same universe of files (.claude-code-hermit/proposals/PROP-*.md, the operator's MEMORY.md index, the 3 most recent session reports, OPERATOR.md, .claude-code-hermit/compiled/*.md) applies to every candidate in the batch. Glob and Read each source once per dispatch, then check every candidate's title/keywords against that cached set — do not re-Glob or re-Read the same source per candidate. Evaluate each candidate independently through Steps 1–5 against the cached reads; reason about all candidates in thinking, then emit one verdict block per candidate in Output.

Your private memory

Your own MEMORY.md is auto-injected into your context by the platform. It holds suppression patterns you have learned across invocations — terse heuristics keyed to suppression codes (weak-recurrence, weak-consequence, not-actionable). Use them to recognize familiar shapes faster during Step 5.

Read the full file on GitHub · 139 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. 2d ago First seen · 139 lines · 123 tokens per session scan A 988733ca93dd

Subscribe to this mod's changes

proposal-triage is an agent published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 123 tokens to every session and 2,598 once invoked, about $0.0006 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 2026-08-30.