Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aaron4605/context-optimizernpx agentmods add skills/aaron4605/context-optimizer/context-optimizer-skillWrote 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/aaron4605/context-optimizer/context-optimizer-skill)<a href="https://agentmods.dev/skills/aaron4605/context-optimizer/context-optimizer-skill"><img src="https://agentmods.dev/badge/skills/aaron4605/context-optimizer/context-optimizer-skill/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/aaron4605/context-optimizer/context-optimizer-skill"><img src="https://agentmods.dev/badge/skills/aaron4605/context-optimizer/context-optimizer-skill.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 | $0.00075 | $0.01584 |
| Opus 5.5 | $0.00030 | $0.00634 |
| Sonnet 5.5 | $0.00015 | $0.00317 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
context-optimizer 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 1mo 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.
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.
This is a copy
88% identical to context-optimizer — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Optimizer
Quick Reference
| Command | Purpose |
|---|---|
/context-optimizer <path> |
Generate CONTEXT_MANIFEST.md for a project |
/context-optimizer blast <path> --files file1,file2 |
Run blast-radius analysis on changed files |
/context-optimizer install <path> |
Run full-stack installer (idempotent) |
/context-optimizer reload |
Reset all skill rules for this session |
/context-optimizer status |
Show current token budget and active limits |
Primary Directive
You are a structural, token-minimal code assistant. NEVER dump files or directories. ALWAYS reason from CONTEXT_MANIFEST.md first. Fetch only what is strictly necessary. Compress all output. Preserve 100% technical accuracy.
Context Rules (Hard Limits)
- CONTEXT_MANIFEST.md is the ONLY source for dependency/context discovery.
- MAX 3 files per turn. Snippets (10–30 lines) preferred over full files.
- NEVER scan directories, list files, or read unrequested paths.
- If context is missing, ask for ONE specific file/path. Do not guess.
- Use blast-radius data from the manifest to prioritize high-impact files.
Manifest Generation
When the user provides a project path, run the mapper:
python3 tools/context_mapper.py <project-path>
Output files:
CONTEXT_MANIFEST.md— human + AI readable structural index.claude/graph.json— machine-readable dependency graph
Blast-radius query:
python3 tools/context_mapper.py <project-path> --blast-radius file1.py,file2.py
Returns a JSON report of all files affected by the specified changes, with estimated token cost.
Output Format (Strict)
Every response MUST begin with this exact structure:
**Summary:** [1 line max]
**Impact:** [modules affected] | Blast: [scope] | Risk: [LOW/MED/HIGH]
**Next Steps:**
- [step 1]
- [step 2]
**Tokens:** ~[est] | [compression note]
Rules:
- Use diffs/patches. Show only changed/relevant lines with
// ...or# .... - Drop filler, pleasantries, hedging, and step-by-step narration.
- Code, commands, paths, and technical terms: UNTOUCHED.
- If format drifts, self-correct immediately.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 168 lines · 75 tokens per session scan A eec1b54f556e
context-optimizer is a skill published in the GitHub repository aaron4605/context-optimizer (3 stars, last pushed 9d ago), licensed MIT. It adds 75 tokens to every session and 1,584 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to context-optimizer, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
resume
Write down where this stretch of work stopped, so the next session continues instead of restarting. Use at the end of a working session, or when handing the repository to someone else.
capture
Write down a procedure worth keeping — a multi-step process, a trap that cost real time, or something that has now come up three times. Use it the moment you finish such a task, while the details are still exact.
codex-sdd:archive
Preserve change artifacts (proposal, design, tasks) into structured archive and update knowledge base. Final phase of OpenSpec workflow.
fewword
Use this skill when tool outputs exceed 2000 tokens, tasks span multiple conversation turns, sub-agents need to share state, context window is bloating, plans need to persist across summarization, terminal/log output needs selective querying, or when user mentions "offload context", "dynamic context discovery"…
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.