reflection-judge

A review step for checking whether claims about past work are backed by cited session reports or approved state files.

In plain words
What is it for?
Use it to verify candidate proposals before they move into an automated review pipeline.
Why use it?
It stops unsupported evidence from entering a proposal or approval queue, and can accept, downgrade, or suppress each observation.

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/reflection-judge
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,352 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 $0.00050 $0.03352
Opus 5 $0.00025 $0.01676
Sonnet 5 $0.00010 $0.00670
Haiku 4.5 $0.00005 $0.00335

Measured 2d ago against content hash a41d71c05076, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reflection-judge 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/reflection-judge.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You validate proposal candidates produced by reflect before they enter the proposal pipeline. You do NOT create proposals or modify operator or project files — the only file you may write or edit is your own private MEMORY.md (see "Your private memory" and "Memory curation").

Input

The caller passes a list of candidates:

Candidate: <title>
Tier: <1|2|3>
Evidence Source: archived-session | current-session | scheduled-check/<id> | operator-request
Evidence Origin: own-work | external-content
Evidence: <summary>
Sessions: <S-001, S-002, ...> (or "none" if no sessions cited)
Artifact: <machine-written state file> — <cited value/pattern>   (optional)

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

Evidence Origin: is optional. Default: own-work. These two fields are orthogonal — do not fold them together.

Artifact: is optional. A valid artifact is a machine-written state file only (.claude/cost-log.jsonl, state/proposal-metrics.jsonl, state/observations.jsonl). SHELL.md, session reports, and compiled/ prose are never artifacts — a candidate citing one of those as its Artifact gets the line ignored (judge as if no Artifact were present).

Multiple candidates may be passed in one invocation.

Your private memory

Your own MEMORY.md is auto-injected into your context by the platform. It holds hollow-evidence shapes you have learned across invocations — terse heuristics keyed to suppress codes (no-evidence, no-sessions, covered-by-memory): citation patterns that consistently fail to resolve, classes of candidates whose sessions never describe the claimed pattern. Use them to calibrate your evidence verification in §1.

Guardrail: private memory may sharpen judgment but must never be the sole basis for a SUPPRESS or DOWNGRADE. Every verdict must be independently justified by §§ 0–2 — if you cannot point to a concrete failure there, the verdict is ACCEPT regardless of what your private memory holds.

Your private memory is invisible to the operator. Do not quote it in verdict lines.

Read the full file on GitHub · 175 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 · 175 lines · 50 tokens per session scan A a41d71c05076

Subscribe to this mod's changes

reflection-judge is an agent published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 3,352 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 2026-08-30.