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.
npx skills add irfad7/claude-power-skills --skill kairos-sessiongit clone --depth 1 https://github.com/irfad7/claude-power-skillsWrote 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.
[](https://agentmods.dev/skills/irfad7/claude-power-skills/kairos-session)<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/kairos-session"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/kairos-session/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/kairos-session"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/kairos-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.01685 |
| Opus 5 | $0.00047 | $0.00843 |
| Sonnet 5 | $0.00019 | $0.00337 |
| Haiku 4.5 | $0.00009 | $0.00169 |
Grade A, and why
kairos-session 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KAIROS Session — Intelligent Session Lifecycle
You are a session lifecycle manager. You handle the ritual of starting and ending work sessions — loading the right context, detecting what's changed, and consolidating learnings when the session ends.
Two Modes
Mode 1: Session Boot (/kairos boot or session start)
Execute this sequence:
Step 1: Context Loading
Read all context files in priority order:
Tier 1 (Identity — always):
1. Project instructions file (CLAUDE.md, AGENTS.md, etc.) — who you are, project rules
2. GRAVITY.md or equivalent — current priorities
3. PULSE.md or equivalent — live state
Tier 2 (Context — always):
4. WORLDMODEL.md — full system map
5. RELATIONSHIPS.md — people context
6. INSTINCT.md — patterns and reflexes
Tier 3 (On-demand — load if relevant):
7. Domain-specific files based on likely task
If the project doesn't use kai-style files, adapt:
- Check for auto-memory directories (
.claude/projects/*/memory/,.cursor/, etc.) - Check for project instruction files (
CLAUDE.md,AGENTS.md,README.md,docs/) - Check git log for recent activity
- Check for any project-specific context files
Step 2: State Diffing
Compare current state against last known state:
Check:
- Which context files changed since last session? (git diff, modified dates)
- Are any context files stale? (not updated in 3+ days when they should be)
- Are there new untracked files that might be important?
- What happened in git since last session? (commits by others, PRs merged)
- Are there any active PRs or issues assigned to the user?
Flag changes:
Since your last session:
- GRAVITY.md was updated — priorities shifted: [summary]
- 3 commits merged to main by [collaborator]
- PULSE.md is 5 days stale — may need refresh
- New file added: src/auth/middleware.ts
Step 3: Calendar & Time Awareness
If calendar access is available:
- What meetings are coming up today?
- Are there deadlines approaching?
- Is there a standup/review soon that needs prep?
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.
- 12d ago First seen · 212 lines · 94 tokens per session scan A 02777b983971
kairos-session is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,685 once invoked, about $0.0005 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.
Other skills, from other repositories
report
Writes the session final report to a file, then prints only the path and a one-line summary. Fires when the prompt contains "Report per memstack:report", and also when the prompt begins with a standing trigger configured through MEMSTACKREPORTONTASKPROMPTS or MEMSTACKREPORTTRIGGERS. Dormant otherwise.
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…
compress
Use when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
grimoire
Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.
catchup
Restore context after /clear by summarizing recent work and project state.