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.
npx skills add egorfedorov/claude-context-optimizer --skill project-contextgit 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/skills/egorfedorov/claude-context-optimizer/project-context)<a href="https://agentmods.dev/skills/egorfedorov/claude-context-optimizer/project-context"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/project-context/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/egorfedorov/claude-context-optimizer/project-context"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/project-context.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 | $0.00081 | $0.00495 |
| Opus 5.5 | $0.00032 | $0.00198 |
| Sonnet 5.5 | $0.00016 | $0.00099 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
project-context 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 yesterday.
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
Project context
Context pasted into every new chat is paid for again in every chat, and drifts each time it is retyped. Written once as instructions, it costs nothing to bring along and stays the same.
Collect
From this conversation, gather what the user keeps supplying: who they are and what they work on, the audience, rules and constraints, tone and format preferences, terms and names, recurring reference material. Ask one question at most, and only for something essential that isn't in the conversation.
Write two things, in the user's language
1. Instructions, in one code block, under 250 words: short imperative lines grouped as Context, Always, Never and Output. Keep only what changes the answers. No pleasantries, no restating what Claude does anyway.
2. Reference material: the long texts (a style guide, a spec, a glossary, a price list) listed by name, to upload as files rather than paste into the instructions.
Where it goes
- claude.ai or the desktop app: create a Project, paste the instructions into its custom instructions, and add the reference files to its knowledge. Every chat started in that Project begins with both. For preferences that apply everywhere, use Settings → Profile instead.
- Cowork: start each task with the instructions, and keep the reference files in the folder you give it.
- Claude Code: a
CLAUDE.mdloads into every session, so keep there only the lines that matter on most tasks (build and test commands, conventions, hard rules). Long references belong in files thatCLAUDE.mdpoints to, read when needed.
End with one line on what this saves: for example, "This replaces the ~1,200-token briefing you've been pasting into each new chat."
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.
- yesterday First seen · 45 lines · 81 tokens per session scan A 99088c5e8b0b
project-context is a skill published in the GitHub repository egorfedorov/claude-context-optimizer (117 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 495 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 2026-10-18.
Other skills, from other repositories
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
alive:my-context-graph
Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.