update-claude-md

update-claude-md is a skill for Claude Code from tta-lab/ttal-cli. It costs 19 tokens per session (425 once invoked), scanned A, original, MIT.

A skill for recording important decisions, preferences, and project conventions in a project’s CLAUDE.md instruction file. It updates the correct file and avoids repeating information already documented.

In plain words
What is it for?
Use it after deciding on workflows, tools, file locations, coding conventions, or other project instructions that future agents should remember.
Why use it?
It preserves useful context from a conversation so future coding sessions can follow the same decisions and working rules.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the ttal plugin — 18 skills, 1 hook shipped together

Good fit Use it after deciding on workflows, tools, file locations, coding conventions, or other project instructions that future agents should remember.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tta-lab/ttal-cli/update-claude-md
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.

Any agent
npx skills add tta-lab/ttal-cli --skill update-claude-md
Clone the repo
git clone --depth 1 https://github.com/tta-lab/ttal-cli

Made for: Claude Code.

Or install ttal, the plugin that ships this one along with the rest of its 18 skills, 1 hook.

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 update-claude-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/tta-lab/ttal-cli/update-claude-md.svg)](https://agentmods.dev/skills/tta-lab/ttal-cli/update-claude-md)
Your own site
<a href="https://agentmods.dev/skills/tta-lab/ttal-cli/update-claude-md"><img src="https://agentmods.dev/badge/skills/tta-lab/ttal-cli/update-claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 425 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00019 $0.00425
Opus 5 $0.00010 $0.00212
Sonnet 5 $0.00004 $0.00085
Haiku 4.5 $0.00002 $0.00042

Measured 7d ago against content hash 0399847c2756, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

update-claude-md 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 7d 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.

skills/update-claude-md/SKILL.md · 50 lines

What it actually says

Update CLAUDE.md

Overview

After a meaningful conversation — decisions made, patterns discovered, preferences stated — the user may ask you to capture what was discussed into the project's CLAUDE.md. This ensures future sessions benefit from today's context.

Which CLAUDE.md?

Find the CLAUDE.md you own in the current repo:

  • In ~/clawd/ — update your agent file (e.g. yuki/CLAUDE.md, kestrel/CLAUDE.md)
  • In any other repo — update the project root CLAUDE.md

If unsure, ask which file to update.

How to Update

  1. Review the conversation — identify decisions, preferences, patterns, or conventions that were established
  2. Read the current CLAUDE.md — understand what's already documented
  3. Add only what's new — don't duplicate existing content
  4. Place it in the right section — match the file's existing structure. Create a new section only if nothing fits.
  5. Be concise — write it as an instruction, not a narrative. Future agents need to act on it, not read a story.

What to Capture

  • Workflow decisions ("always use X instead of Y")
  • Tool preferences ("use og pr, not gh")
  • Conventions discovered ("tests go in tests/ not test/")
  • Architecture decisions ("we chose X because Y")
  • Gotchas and warnings ("don't run Z, it breaks W")

What NOT to Capture

  • Session-specific details (current task, in-progress work)
  • Anything already in CLAUDE.md (check first!)
  • Speculative conclusions from one conversation
  • Temporary workarounds (unless they'll persist)

After Updating

  • Show the user what you added/changed
  • Commit if asked (follow the repo's commit conventions)
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. 7d ago First seen · 50 lines · 19 tokens per session scan A 0399847c2756

Subscribe to this mod's changes

update-claude-md is a skill published in the GitHub repository tta-lab/ttal-cli (23 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 425 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens