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 agentmods add skills/cheswickdev/cairn/cairn-helpnpx skills add CheswickDEV/cairn --skill cairn-helpgit clone --depth 1 https://github.com/CheswickDEV/cairnWhat 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 | $0.00063 | $0.00553 |
| Opus 5 | $0.00032 | $0.00277 |
| Sonnet 5 | $0.00013 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
Cairn Help 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 yesterday.
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.
What it actually says
Cairn Help — quick reference
When the user says "Cairn Help" (or asks what Cairn can do), show this overview verbatim:
Trigger phrases — say these in chat, the agent acts
| Say… | What happens |
|---|---|
| Cairn resume | Re-inject the ledger (decision_log view=current) and continue from it as the source of truth — without re-reading the repo. |
| Cairn Handoff | Author a 7-bucket brief from the conversation and persist it via handoff (local, no egress). |
| Cairn Help | Show this table. |
MCP tools — the agent calls these directly (Codex has no statusline/hooks, so call them yourself)
| Tool | Purpose |
|---|---|
decision_log |
Read / re-inject the ledger. view:"current" = lean resume state; view:"all" = full history + evidence. |
handoff |
Persist a host-written 7-bucket brief (account mode = no model call, nothing leaves the host). |
context_status |
Report the zone (🟢/🟡/🔴) relative to the active window (pass the host model_context_window, e.g. 258400, as surfaceCap). |
host_status |
Which host CLIs are logged in + the active model. |
Shell command — you, in the terminal
| Command | What it shows |
|---|---|
cairn status |
One-line zone of the active Codex session (e.g. 🟢 21% ctx · gpt-5.5). |
cairn window |
Live zone strip as a split pane (Windows Terminal / tmux / iTerm2). |
cairn tab / cairn stop |
Zone in the terminal title / stop it. |
cairn list |
All recent Codex sessions (pin one with --session <uuid>). |
Cairn is a local-private continuity engine: it persists decisions + evidence across sessions/models and warns before the context window degrades. In the default account mode nothing leaves the host.
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.
- yesterday First seen · 38 lines · 63 tokens per session scan A 2eee437d7e6d
Cairn Help is a skill published in the GitHub repository CheswickDEV/cairn (1 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 553 once invoked, about $0.0003 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
kn-debug
Use when debugging errors, test failures, build issues, or blocked tasks — structured triage to fix to learn.
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.
kn-init
Use at the start of a new session to read project docs, understand context, and see current state.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.