breathe

breathe is a skill for Claude Code, Codex from tta-lab/ttal-cli. It costs 14 tokens per session (886 once invoked), scanned A, original, MIT.

A session handoff procedure for restarting an agent with a fresh context window. It records the task, completed work, decisions, current state, and next steps before asking TTAL to restart the session.

In plain words
What is it for?
Writing a handoff note and restarting an ongoing TTAL task without losing its status, file locations, decisions, or remaining work.
Why use it?
It preserves important working details when a conversation becomes too large for the current context.

Skill for Claude CodeCodex

Part of the ttal plugin — 18 skills, 1 hook 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 skills/tta-lab/ttal-cli/breathe
Any agent
npx skills add tta-lab/ttal-cli --skill breathe
Clone the repo
git clone --depth 1 https://github.com/tta-lab/ttal-cli

Made for: Claude Code, Codex.

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 breathe

README.md
[![agentmods](https://agentmods.dev/badge/skills/tta-lab/ttal-cli/breathe.svg)](https://agentmods.dev/skills/tta-lab/ttal-cli/breathe)
Your own site
<a href="https://agentmods.dev/skills/tta-lab/ttal-cli/breathe"><img src="https://agentmods.dev/badge/skills/tta-lab/ttal-cli/breathe.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 886 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 $0.00014 $0.00886
Opus 5 $0.00007 $0.00443
Sonnet 5 $0.00003 $0.00177
Haiku 4.5 $0.00001 $0.00089

Measured 5d ago against content hash 200582e7e99b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

breathe 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.

skills/breathe/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Breathe — Session Handoff

When your context window is getting heavy, use this to write a handoff to your diary and restart your session with a clean context window. You keep all important state — just shed the conversation weight.

Announce at start: "Taking a breath — writing handoff for session restart."

Usage

/breathe

Steps

  1. Write the handoff to your diary via heredoc into diary <agent> append
  2. Call ttal breathe (no arguments)
  3. Stop — the daemon will kill this session and restart you with a fresh context window

How to Call

cat <<'HANDOFF_EOF' | diary $TTAL_AGENT_NAME append

Session Handoff

Active Task

[task UUID, description, current status]

What Was Done

[bullet list — files changed, decisions made]

Key Decisions

[architecture choices, trade-offs, approach and why]

Current State

[where you left off — file, step in plan, what you're waiting for]

Next Steps

[ordered list of what to do next]

Important Context

[non-obvious things that would be lost — gotchas, workarounds] HANDOFF_EOF

ttal breathe

Quality Checklist

  • Task UUID included (not just description)
  • Specific file paths (not "the config file")
  • Decisions include the why
  • Next steps are actionable without previous context
  • Self-contained — no "earlier in this conversation" references

What NOT to Include

  • Full file contents (new session can read files)
  • Conversation history or back-and-forth
  • Completed work that doesn't affect next steps
  • Tool output or logs (summarize instead)

Target: 50-200 lines — enough to be useful, short enough to leave room for work.

What Happens After

Manager path

  1. The daemon receives your ttal breathe request
  2. Status file session ID is cleared
  3. Your session is killed
  4. A new session starts fresh (same runtime, no resume)
  5. Your spawn trigger says to run ttal context for your briefing
  6. ttal context picks the manager template, renders it (diary read, agent list, project list, pairing, role prompt, task), and prints the bundle
  7. You wake up in a fresh context window

Read the full file on GitHub · 107 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 · 107 lines · 14 tokens per session scan A 200582e7e99b

Subscribe to this mod's changes

breathe is a skill published in the GitHub repository tta-lab/ttal-cli (23 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 886 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

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 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

Migrate

Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with…

danielmiessler/LifeOS · 158 tokens

release

Cut a versioned release and publish everos to PyPI via the tag-triggered workflow.

EverMind-AI/EverOS · 20 tokens

personal-assistant

A personalized assistant that remembers your preferences.

NVIDIA/SkillSpector · 11 tokens

daily-briefing

Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…

vellum-ai/vellum-assistant · 75 tokens