Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add isaacriehm/cairn/plugin install cairnWrote 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/commands/isaacriehm/cairn/cairn-statusline-setup)<a href="https://agentmods.dev/commands/isaacriehm/cairn/cairn-statusline-setup"><img src="https://agentmods.dev/badge/commands/isaacriehm/cairn/cairn-statusline-setup.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.01794 |
| Opus 5 | $0.00012 | $0.00897 |
| Sonnet 5 | $0.00005 | $0.00359 |
| Haiku 4.5 | $0.00002 | $0.00179 |
Grade B, and why
cairn-statusline-setup scanned grade B with 2 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Wire this developer's `~/.claude/settings.json` statusline to the Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
"command": "node -e \"const f=require('node:fs'),{homedir}=require('node:os'),{join}=require('node:path'),{spawnSync}=require('node:child_process');const C=join(homedir(),'.claude','plugins','cache');const newest=a=>{let How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cairn:cairn-statusline-setup
Wire this developer's ~/.claude/settings.json statusline to the
cairn bundle. Once configured, every Claude Code session shows a
compact one-line badge in the prompt's status row:
⬡ cairn [signal] [ctx-meter pct%]
Signal priority (first match wins):
⏳ adopt <phase> X/Y (P%) ~Nm— live during cairn-adopt long phases⚠ N unattested— bypass commits since cairn init⚑ N pending— pending decision drafts in attention queue◐ gc— GC sweep in progressTSK-... <title>— active task in flight✓ N·M— idle heartbeat showing N decisions and M invariants in scope (positive signal that Cairn is alive)- (empty) — fresh adoption with no ground state yet; just brand + ctx meter
Step 1 — surface the inline prompt
Render via AskUserQuestion:
Wire the cairn statusline into your user-level settings? It shows a one-line ground-state summary in every Claude Code session.
[a]set it up now[b]skip — re-run/cairn:cairn-statusline-setuplater
Step 2 — locate the shim file
The plugin's SessionStart hook writes the bundle's current path to
~/.claude/plugins/cache/<slug>/.active-version-path on every session
open, where <slug> is the marketplace name Claude Code installed the
plugin under. The shim is a single line: the absolute path to the
active dist/cli.mjs. Resolve it with a Node glob over
~/.claude/plugins/cache/*/.active-version-path that picks the
most-recently-written shim by mtime — never hardcode the slug:
const { readdirSync, statSync } = require('node:fs');
const { homedir } = require('node:os');
const { join } = require('node:path');
const base = join(homedir(), '.claude', 'plugins', 'cache');
let shim = null, newest = 0;
for (const slug of readdirSync(base)) {
const p = join(base, slug, '.active-version-path');
try {
const m = statSync(p).mtimeMs;
if (m >= newest) { newest = m; shim = p; }
} catch {}
}
If empty, the plugin's SessionStart hook hasn't fired even once for the current install. Surface this enumerated cause list:
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.
- 8d ago First seen · 142 lines · 23 tokens per session scan B 648676e253fe
cairn-statusline-setup is a command published in the GitHub repository isaacriehm/cairn (6 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,794 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
update
Update the Hivemind plugin to the latest version.
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).
plan
Show or update the work ledger — what is done, in flight, and next.
rosetta-grill
Grill the user about a plan or design — but grounded in Rosetta's resolved decision state — then RECORD the outcome as an ADR/PDR. Use when the user wants to stress-test a decision, says "grill me on this", or wants a decision interrogated and captured. Integrates grill-me-style interrogation with Rosetta's…
rosetta-preflight
Produce Rosetta's deterministic preflight JSON for a scoped change: optional RA1 structural report, decision-state resolution, and local Rosetta gates. Use before handing execution to a loop runner.
seed
Inspect the codebase and propose starter areas + topics for the wherefore log.