context-os
Cut Claude Code token usage by 40.9%. A 400-line Python hook that builds a static graph of your repo (symbols + imports + git-hot files) and injects ranked file:line candidates into the prompt before Claude sees it. So the first turn opens the right file instead of grepping for it.
No embeddings. No server. No model call. ~50 ms.
Need this applied to a private repo this week? Fund the $1,000 48-hour implementation sprint or read the audit scope. The OSS tool stays free; the sprint is for teams that want a private report, CI leak gate, and one concrete repo/workflow patch.
curl -fsSL https://raw.githubusercontent.com/sravan27/context-os/main/setup.sh | bash
60-second demo: graph stats → autocontext block with import counts → cross-repo eval (auto_context 0.545 winning) → 9/9 CI floors PASS. Reproduce with bash docs/distribution/demo.sh.
Private repo audit
If your team is already spending heavily on Claude Code, Codex, Cursor, or other coding agents and wants a private cost-leak report, I am doing a small number of 48-hour audits this week: AI Agent Cost Leak Audit.
The open-source hook stays MIT and free. The paid audit is for teams that want the same measurement discipline applied to their own repo, prompts, and agent workflows.
What the paid sprint ships:
- a private repo scorecard using the same leak signals as the Action
- a short report on the highest-cost agent loops and file-noise sources
- one concrete CI, ignore-rule, or repo-guidance patch where the fix is clear
- a handoff note your team can reuse when running Claude Code, Codex, Cursor, or internal agents
Quick local preview:
python3 python/agent_cost_leak_check.py --repo . --json
CI recipe: docs/AGENT-COST-LEAK-CHECKER.md. For public intake without sharing private code, use the private audit request template.
Versioned GitHub Action:
- uses: sravan27/context-os@v2.9.0
with:
max-score: "40"
The number
Live A/B on 36 real claude --print calls, identical fixture, identical model, only difference is whether the hook is active:
| Metric | Value |
|---|
| Aggregate tokens | −40.9% |
| Prompt-level wins | 6/6 |
| Bootstrap 95% CI | 32.7%–48.9% |
| Paired t-test | p = 5.1e-7 |
| Wall-clock | −35.3% |
Raw JSON for every call: python/evals/reports/live-session-bench-raw.json · methodology: docs/METHODOLOGY.md.
Cross-repo: 36 hand-labeled prompts × 3 unseen OSS repos (axios, ripgrep, requests). Weighted MRR 0.545 vs 0.461 best lexical baseline — +18.2%. Beats every baseline in every language. Report: multi-repo-eval.md.
What Claude sees
Before:
user: where is the gitignore parser
claude: Glob → Grep → Read → Read → Read → "found it in walk.rs"
After:
<context-os:autocontext>
crates/ignore/src/gitignore.rs:42 · Gitignore (struct)
crates/ignore/src/gitignore.rs:118 · matched (fn) · imports: …
</context-os:autocontext>
claude: Read crates/ignore/src/gitignore.rs → done
Install
Per-project:
curl -fsSL https://raw.githubusercontent.com/sravan27/context-os/main/setup.sh | bash
Global response-shaping + env vars to ~/.claude/:
curl -fsSL https://raw.githubusercontent.com/sravan27/context-os/main/setup.sh | bash -s -- --global
Reproduce the eval locally:
git clone https://github.com/sravan27/context-os && cd context-os
python3 python/evals/runners/ranker_floor.py # 9 CI-enforced floors, ~45s
python3 python/evals/runners/multi_repo_eval.py # cross-repo eval, ~2 min
What it installs
setup.sh writes 28 techniques across CLAUDE.md, .claudeignore, .claude/settings.json, eleven slash commands, an output style, a Haiku explorer subagent, and six stdlib-Python hooks under .claude/hooks/. Full list with evidence per row: docs/TECHNIQUES.md.
