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 cdeust/session-optimizer/plugin install statuslineWrote 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/cdeust/session-optimizer/statusline)<a href="https://agentmods.dev/skills/cdeust/session-optimizer/statusline"><img src="https://agentmods.dev/badge/skills/cdeust/session-optimizer/statusline/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/cdeust/session-optimizer/statusline"><img src="https://agentmods.dev/badge/skills/cdeust/session-optimizer/statusline.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 | $0.00067 | $0.01588 |
| Opus 5.5 | $0.00027 | $0.00635 |
| Sonnet 5.5 | $0.00013 | $0.00318 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade B, and why
statusline scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f "$root/install.sh" ] || root=$(find ~/.claude/plugins/cache -type f -path '*/statusline/*/install.sh' 2>/dev/null | sort | tail -1 | xargs -I{} dirname {}) How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Statusline install
Installs the multi-line statusline that shows model + git context, a discrete heat-track context bar tied to per-model checkpoint thresholds, session cost and duration from one deduplicated ledger, 5h/7d rate-limit gauges with burn-rate pacing, per-session telemetry (tok/s, compactions, prompt-cache countdown), and live subagent activity, every line fitted to the terminal width.
The plugin ships one installer, install.sh at the plugin root. It is the
only thing that writes the statusline's files, the SessionStart hook runs the
same script in sync mode after every plugin update, and it is deterministic:
no file is compared or copied by hand.
What ends up on disk
~/.claude/statusline/ the whole install, one directory
statusline-command.sh renderer entry point (composition root)
lib/*.sh its modules, one concern per file
costs.sh pricing.json cost ledger CLI and the prices it uses
transcript.py per-session telemetry, backgrounded (15 s TTL)
README.md this plugin's README
statusline-budget.json PERSONAL config: seeded once, never overwritten
state/ everything written at runtime
costs.jsonl the ledger (+ .lock, .cleanup-stamp while running)
sessions/<session>.main|.sub per-session price caches, 30-day retention
transcript-cache.json telemetry cache
backup/<timestamp>/ superseded files, newest 3 runs kept
~/.claude/ctxguard-thresholds.json SHARED with context-guard: stays at the root
ctxguard-thresholds.json is the one file kept at the root of ~/.claude:
the context-guard plugin's Stop hook reads that exact path, and a file with two
readers lives where both find it. Seeded if absent, never overwritten.
An earlier install (everything flat at the root of ~/.claude) is
migrated once by the same script: files are moved, not copied, the ledger
and its per-session caches keep their content and timestamps, and the root is
left to Claude Code.
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.
- 2mo ago Changed · -29 lines 59e519964ed4
- 2mo ago First seen · 158 lines · 67 tokens per session scan B add99b829341
statusline is a skill published in the GitHub repository cdeust/session-optimizer (1 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 1,588 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
statusline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| statuslinecdeust/session-optimizer | Skill | 1 | 2d ago | MIT | B | 67 | Claude Code |
| resolve-pluginsRockyHong/super-bootstrap | Skill | 3 | yesterday | MIT | A | 135 | Claude Code |
| journey-simulationRockyHong/super-bootstrap | Skill | 3 | yesterday | MIT | A | 79 | Claude Code |
| check-docs-consistencyRockyHong/super-bootstrap | Skill | 3 | yesterday | MIT | A | 34 | Claude Code |
| mergeRockyHong/super-bootstrap | Skill | 3 | yesterday | MIT | A | 130 | Claude Code |
| releaseRockyHong/super-bootstrap | Skill | 3 | yesterday | MIT | A | 24 | Claude Code |
| release-initRockyHong/super-bootstrap | Skill | 3 | yesterday | MIT | A | 25 | Claude Code |