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 Cynrath/agent-context-kit --skill ackit-context-optimizationgit clone --depth 1 https://github.com/Cynrath/agent-context-kitWrote 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/cynrath/agent-context-kit/ackit-context-optimization)<a href="https://agentmods.dev/skills/cynrath/agent-context-kit/ackit-context-optimization"><img src="https://agentmods.dev/badge/skills/cynrath/agent-context-kit/ackit-context-optimization/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/cynrath/agent-context-kit/ackit-context-optimization"><img src="https://agentmods.dev/badge/skills/cynrath/agent-context-kit/ackit-context-optimization.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 | $0.00020 | $0.00366 |
| Opus 5.5 | $0.00008 | $0.00146 |
| Sonnet 5.5 | $0.00004 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
ackit-context-optimization 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.
What it actually says
Context Optimization
Activate when the user asks to prepare context for an agent session or reduce token usage.
See ranking signals for deterministic ordering.
Steps
ackit pack --max-tokens <budget> [--format markdown|json] [--include <globs...>] [--changed] [--profile codex|claude|copilot|gemini|generic] [--task <id>] [--resume]to generate a deterministic pack with a manifest of included/excluded files and reasons (relativePath,action,reason,estimatedTokens,sha256,bytes). Task-aware ranking (--task) and checkpoint resume (--resume) keep packs scoped; greedy fill excludes over-budget candidates withbudget exhausted.- Review exclusions; add explicit includes only when the ranking missed real relevance (explicit include is the highest signal; no embeddings).
- For bloated instructions, run
ackit optimize [--profile <name>] [--category <cat>] [--min-severity low|medium|high] [--explain] [--format terminal|json|markdown|sarif](read-only by default) and apply suggestions manually or withackit optimize --fix [--dry-run] [--diff]— fixes apply ONLY to ACKit-managed surfaces.
Notes
- Token counts are character-class estimates (~4 chars/token); treat budgets as soft targets.
- Safety gates run before scoring: secret-shaped content excluded, duplicate hashes deduped, machine-local paths scrubbed to
<local-path>. - Never paste repository content into external services.
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 Changed 979007f74fb8
- 1mo ago First seen · 24 lines · 20 tokens per session scan A 1def1ee184f5
ackit-context-optimization is a skill published in the GitHub repository Cynrath/agent-context-kit (14 stars, last pushed 12d ago), licensed MIT. It adds 20 tokens to every session and 366 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
git-ai-search
Search and restore AI conversation context from git history.
remember
Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log, then draft only the root pages that have meaningful content and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
immune
Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).