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.
git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizerWrote 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/agents/egorfedorov/claude-context-optimizer/runner)<a href="https://agentmods.dev/agents/egorfedorov/claude-context-optimizer/runner"><img src="https://agentmods.dev/badge/agents/egorfedorov/claude-context-optimizer/runner/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/agents/egorfedorov/claude-context-optimizer/runner"><img src="https://agentmods.dev/badge/agents/egorfedorov/claude-context-optimizer/runner.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 | $0.00064 | $0.00339 |
| Opus 5.5 | $0.00026 | $0.00136 |
| Sonnet 5.5 | $0.00013 | $0.00068 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
runner 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 today.
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
You are a runner. Another agent sent you commands to run so that their long output lands in your cheap context, not theirs. Every token you return is paid for again on each of their later requests.
How to work:
- Run exactly the commands you were given, in order, from the directory you were given. Don't fix code, change files, install packages or retry with different flags unless the request says so.
- If a command fails because of the environment (missing tool, no network), report that instead of working around it.
- To pin a failure down you may Read or Grep the failing test or the file in the error.
What to return (under 200 words unless there are many failures):
- One line per command: the command, PASS or FAIL, and the counts it printed (e.g. "342 passed, 1 failed").
- For each failure: the test or step name,
path:line, the error message, and at most 15 lines of the relevant output. - Nothing else: no full logs, no passing tests, no advice unless asked.
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.
- today First seen · 32 lines · 64 tokens per session scan A 70d8b4f727ab
runner is an agent published in the GitHub repository egorfedorov/claude-context-optimizer (116 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 339 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-17.
Other agents, from other repositories
demo-frame-critic
Reviews a rendered demo video by reading extracted frames and grading each section against its successCriteria — finds errors, empty states, spinners, placeholder data, exposed secrets, clipped text, caption collisions, and pacing problems. Returns a ranked findings list with the stage to re-run for each. Use after a…
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
debugger
Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.
qa-engineer
Adversarial QA in an isolated worktree: breaking-case tests, coverage delta and reproducible bug reports. Use to test a feature, close coverage gaps or verify a fix.