self-edit

self-edit is a skill for Claude Code, Codex from ahkedia/lyra-ai. It costs 40 tokens per session (985 once invoked), scanned A, original, MIT.

A Telegram-controlled workflow for changing an assistant’s configuration, memory, personality, scheduled-task context, or individual skill instructions. These are text files that control how the assistant behaves and what it remembers.

In plain words
What is it for?
Use it to update remembered facts, response rules, behaviour, Notion references, scheduled-task context, and skill instructions.
Why use it?
It lets approved changes be made from Telegram without opening an editor such as Cursor.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/akashkedia/.openclaw/workspace/MEMORY.md.

Good fit Use it to update remembered facts, response rules, behaviour, Notion references, scheduled-task context, and skill instructions.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

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 self-edit

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahkedia/lyra-ai/self-edit.svg)](https://agentmods.dev/skills/ahkedia/lyra-ai/self-edit)
Your own site
<a href="https://agentmods.dev/skills/ahkedia/lyra-ai/self-edit"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/self-edit.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 985 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 $0.00040 $0.00985
Opus 5 $0.00020 $0.00492
Sonnet 5 $0.00008 $0.00197
Haiku 4.5 $0.00004 $0.00098

Measured 7d ago against content hash ee6f005d5101, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

self-edit 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/self-edit/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Edit — Lyra Editing Her Own Files

You have permission to modify your own workspace files when Akash instructs you to. This is how you stay up to date and improve without needing Cursor every time.

Your Files and What They Control

File Purpose When to edit
~/.openclaw/workspace/SOUL.md Your personality, rules, communication style, hard limits "Change how you respond", "add a rule", "update your behavior"
~/.openclaw/workspace/MEMORY.md Permanent facts about Akash, Abhigna, context "Remember that...", "update my job status", "add this to your memory"
~/.openclaw/references/notion.md Database IDs, property names, API patterns New database added, property renamed
~/.openclaw/workspace/HEARTBEAT.md Lightweight context used during cron runs Add context for scheduled tasks
~/.openclaw/workspace/skills/*/SKILL.md Individual skill instructions Skill needs updating or fixing

How to Edit a File

Use the bash tool to read and overwrite files. Always read first, then write.

Read a file

cat ~/.openclaw/workspace/SOUL.md

Append a line (for adding a rule or memory item)

echo "\n- New rule or memory item" >> ~/.openclaw/workspace/MEMORY.md

Replace a section (for more surgical edits)

Use Python to read the full file, make the change, and write it back:

python3 << 'EOF'
with open('/Users/akashkedia/.openclaw/workspace/MEMORY.md', 'r') as f:
    content = f.read()
# make your change
content = content.replace('old text', 'new text')
with open('/Users/akashkedia/.openclaw/workspace/MEMORY.md', 'w') as f:
    f.write(content)
print("Done")
EOF

Overwrite a full section

Read the file, find the section boundary, rewrite:

python3 << 'EOF'
with open('/Users/akashkedia/.openclaw/workspace/SOUL.md', 'r') as f:
    content = f.read()
# Show current content
print(content[:500])
EOF

What You Can Change Without Asking

  • Adding new facts to MEMORY.md (e.g., "remember my new job started today")
  • Adding new rules to SOUL.md (e.g., "never suggest Notion for X")
  • Updating your own context about databases, people, or events

Read the full file on GitHub · 115 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. 7d ago First seen · 115 lines · 40 tokens per session scan A ee6f005d5101

Subscribe to this mod's changes

self-edit is a skill published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 18d ago), licensed MIT. It adds 40 tokens to every session and 985 once invoked, about $0.0002 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 skills, from other repositories

memory-processor

Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic…

smixs/iva-agent · 106 tokens

dbrain-processor

Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.

smixs/agent-second-brain · 60 tokens

autograph

Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…

smixs/agent-second-brain · 89 tokens

db-maintenance

A maintenance guide for a SQLite database that stores memories, sessions, and conversation records in one file. SQLite is a database system that can keep data in a single file.

tigu77/tiguclaw · 0 tokens

memory-tidy

A memory-maintenance skill for finding duplicate, expired, or overly long entries in an assistant's memory index. It suggests changes for a person to approve and archives entries instead of permanently deleting them.

tigu77/tiguclaw · 0 tokens

autograph

Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…

smixs/iva-agent · 89 tokens