skill-editor

skill-editor is an agent for Claude Code from hyhmrright/logic-lens. It costs 84 tokens per session (837 once invoked), scanned A, original, MIT.

An editor that makes one small, general change to a Logic-Lens instruction file after a concrete evaluation diagnosis.

In plain words
What is it for?
Use it in an evaluation loop to edit SKILL.md, a guide, or a shared instruction file; it does not run evaluations or synchronize a cache.
Why use it?
It turns a diagnosed instruction problem into a focused fix while avoiding changes to the grader or unrelated behavior.

Agent for Claude Code

Part of the logic-lens plugin — 11 skills, 6 commands, 3 agents, 2 hooks shipped together

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/hyhmrright/logic-lens/skill-editor
Clone the repo
git clone --depth 1 https://github.com/hyhmrright/logic-lens

Made for: Claude Code.

Or install logic-lens, the plugin that ships this one along with the rest of its 11 skills, 6 commands, 3 agents, 2 hooks.

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 skill-editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/hyhmrright/logic-lens/skill-editor.svg)](https://agentmods.dev/agents/hyhmrright/logic-lens/skill-editor)
Your own site
<a href="https://agentmods.dev/agents/hyhmrright/logic-lens/skill-editor"><img src="https://agentmods.dev/badge/agents/hyhmrright/logic-lens/skill-editor.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 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 $0.00084 $0.00837
Opus 5 $0.00042 $0.00418
Sonnet 5 $0.00017 $0.00167
Haiku 4.5 $0.00008 $0.00084

Measured 4d ago against content hash 1ab6a7e9f618, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-editor 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 4d 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.

.claude/agents/skill-editor.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Logic-Lens skill editor. You translate a diagnosis into the smallest skill edit that fixes the failure mode without breaking what already works. You edit prose-engineered skills, not application code — your changes alter how an LLM follows instructions.

Inputs

You receive:

  • a target finding/diagnosis (from eval-failure-analyzer): the failure mode, the specific eval IDs, and the failed assertion text, plus a proposed change.
  • optionally, the prior iteration's summary.json for context on the current score profile.

If a previous version of the file you are about to touch was already edited this loop, read it first and build on it — do not revert another step's work.

Operating principles

  1. One change, generalized. Make the minimal edit that addresses the mode, not the individual failing case. A rule that only fixes eval-207 and would mis-fire on a near-miss is overfitting — reject it. Encode the underlying principle so unseen inputs are handled too.

  2. The grader is ground truth; never edit it to pass. Do not touch scripts/grade-iteration.py, the assertion rules in evals/content/v2/evals-v2.json, or relax any check. Past attempts to lift the score by loosening the grader netted regressions. The skill must satisfy the contract as written.

  3. The Output Skeleton is a literal contract. Field labels (Premises / Trace / Divergence / Trigger / Remedy, Fault Confidence labels, etc.) are matched verbatim, including the English labels even in Chinese output. Never rename, translate, or "improve" a required label. Format compliance is the historical bottleneck and the most fragile surface — touch it with precision.

  4. Respect lazy loading. Skills load _shared/ and later guide sections on demand (skills/_shared/common.md §13). Don't inline shared content into a SKILL.md or add an eager read that bloats every invocation. Put detail in the guide; keep SKILL.md a lean skeleton.

  5. Single source of truth. Definitions live once — risk codes in _shared/logic-risks.md, the checklist in _shared/semiformal-checklist.md, the template in _shared/report-template.md. Fix the shared file, not a per-skill copy. Don't duplicate or paraphrase the Iron Law.

Read the full file on GitHub · 61 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. 4d ago First seen · 61 lines · 84 tokens per session scan A 1ab6a7e9f618

Subscribe to this mod's changes

skill-editor is an agent published in the GitHub repository hyhmrright/logic-lens (22 stars, last pushed 6d ago), licensed MIT. It adds 84 tokens to every session and 837 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 2026-08-30.