heal

heal is a command for Claude Code from arnaudgelas/K-Ops. It costs 5 tokens per session (1,530 once invoked), scanned A, original, MIT.

A repair tool for the structure of a knowledge base made of notes and source files. It fixes organization and metadata while leaving the stored knowledge unchanged.

In plain words
What is it for?
Use it to repair concept pages and source notes, add safe missing fields or empty sections, and record uncertain fixes for later review.
Why use it?
It helps correct broken links, missing sections, and incomplete page details without rewriting claims or adding unsupported information.

Command for Claude Code

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 commands/arnaudgelas/k-ops/heal
Clone the repo
git clone --depth 1 https://github.com/arnaudgelas/K-Ops

Made for: Claude Code.

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 heal

README.md
[![agentmods](https://agentmods.dev/badge/commands/arnaudgelas/k-ops/heal.svg)](https://agentmods.dev/commands/arnaudgelas/k-ops/heal)
Your own site
<a href="https://agentmods.dev/commands/arnaudgelas/k-ops/heal"><img src="https://agentmods.dev/badge/commands/arnaudgelas/k-ops/heal.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,530 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 5.1 $0.00005 $0.01530
Opus 5 $0.00003 $0.00765
Sonnet 5 $0.00001 $0.00306
Haiku 4.5 $0.00001 $0.00153

Measured 5d ago against content hash f7e5d228ba2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

heal 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 5d 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/commands/heal.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the structural repair agent for this knowledge base. You fix structure - you do not rewrite knowledge.


What NOT to do

Read this section before touching any file.

  • Do not rewrite Key Claims bullets or change their meaning.
  • Do not change claim_quality assessments - that is the compiler's job.
  • Do not add or remove source summaries.
  • Do not create new concept pages.
  • Do not invent content to fill sparse pages - add empty scaffolding sections only.
  • Do not touch data/raw/ - those files are immutable.
  • Do not run more than one pass over each directory.

Repair order

  1. Fix broken wikilinks.
  2. Add missing required sections as empty scaffolds.
  3. Add missing frontmatter fields with safe defaults.
  4. Record revalidation-required pages in notes/TODO.md.
  5. On source notes, add evidence_strength, source_id, source_kind, source_status, and ingested_at before anything else.

If you are uncertain whether a fix is safe, record it in notes/TODO.md instead of making it.


One-pass repair protocol

Make exactly one pass over notes/Concepts/ and one pass over notes/Sources/. Then stop.

Pass 1 - Concept pages (notes/Concepts/)

For each concept page, check and fix in this order:

  1. Broken wikilinks - [[Target]] where Target does not exist as a vault file. -> Fix the path if you can determine the correct target (e.g. spaces/hyphens → underscores, add Concepts/ prefix). -> If the target cannot be resolved: convert [[Target]] to plain text Target and add _Concept not yet created: Target_ to the ## Open Questions section. Never silently delete concept vocabulary.

  2. Missing required sections - a concept page must have: ## What It Is, ## Why It Matters, ## Key Claims, ## Related Concepts, ## Evidence / Source Basis, ## Open Questions, and ## Backlinks. -> If a section is missing, add an empty scaffold (e.g., ## Open Questions with _No open questions identified._ or <!-- TODO: populate -->). Do not populate content.

Read the full file on GitHub · 101 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. 5d ago First seen · 101 lines · 5 tokens per session scan A f7e5d228ba2a

Subscribe to this mod's changes

heal is a command published in the GitHub repository arnaudgelas/K-Ops (1 stars, last pushed 17d ago), licensed MIT. It adds 5 tokens to every session and 1,530 once invoked, about $0.0000 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 commands, from other repositories