ackit-context-optimization

A guide for preparing smaller, focused context packs for coding-agent sessions. It can rank relevant files and estimate whether a pack fits a chosen token budget.

In plain words
What is it for?
It is for creating context packs, reviewing which files were included or excluded, and finding ways to shorten oversized instructions.
Why use it?
It reduces the amount of irrelevant repository content an agent must process, which helps keep sessions focused and within context limits.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cynrath/agent-context-kit/ackit-context-optimization
Any agent
npx skills add Cynrath/agent-context-kit --skill ackit-context-optimization
Clone the repo
git clone --depth 1 https://github.com/Cynrath/agent-context-kit

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 158 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.00158
Opus 5 $0.00010 $0.00079
Sonnet 5 $0.00004 $0.00032
Haiku 4.5 $0.00002 $0.00016

Measured 2d ago against content hash 1def1ee184f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

templates/skills/ackit-context-optimization/SKILL.md · 24 lines

What it actually says

Context Optimization

Activate when the user asks to prepare context for an agent session or reduce token usage.

Steps

  1. ackit pack --max-tokens <budget> to generate a deterministic pack with a manifest of included/excluded files and reasons.
  2. Review exclusions; add explicit includes only when the ranking missed real relevance.
  3. For bloated instructions, run ackit optimize (read-only) and apply its suggestions manually or with --fix inside managed blocks.

Notes

  • Token counts are estimates; treat budgets as soft targets.
  • Never paste repository content into external services.
Files

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.

Changes

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.

  1. 2d ago First seen · 24 lines · 20 tokens per session scan A 1def1ee184f5

Subscribe to this mod's changes

ackit-context-optimization is a skill published in the GitHub repository Cynrath/agent-context-kit (14 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 158 once invoked, about $0.0001 per session on Opus 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.

Related

Other skills, from other repositories

onboard-repository

Inspect an unfamiliar or brownfield repository, trace one real operational path, and propose evidence-backed improvements that help future agents work independently. Use when explicitly asked to onboard, map, assess, or backfill agent-facing repository guidance; use again after the user approves exact proposal items.…

hoangnb24/repository-harness · 87 tokens

improve-harness

Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…

hoangnb24/repository-harness · 76 tokens

steadyagent-workflow

Local-first Codex workflow for planning, debugging, reviewing, refactoring, improving AGENTS.md, building skills, publishing agent harness repositories, or running complex multi-step coding tasks that need staged diagnosis, context control, verification loops, review strategy, release evidence, and…

Khalilzhang0825/boring-is-all-you-need · 64 tokens

agents-doctor

Validate AGENTS.md and related agent instruction files with the published agents-doctor CLI. Use when the user asks to check, lint, verify, explain, audit, fix, release-check, or compare AGENTS.md, CLAUDE.md, GEMINI.md, agent instruction inheritance, tool profiles, context fidelity, instruction graphs, GitHub…

ItsHege/agents-md-doctor · 93 tokens

agent-loader

Load or list repo-scoped and user-scoped agent brains. Use when the user asks to load an agent by name, list available agents, inspect agent descriptions or workflows, or start a session or task with a personal agent brain.

samzong/agent-brains · 50 tokens

openpets

Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpetsstatus, openpetsreact, or openpetssay.

alvinunreal/openpets · 70 tokens