A local auditing and reporting toolkit for the context available to OpenAI Codex, including instructions, skills, agents, and connected tools. It can also inspect prompts, model profiles, configuration changes, and usage limits.

Run context health checks, inventory configuration, inspect prompt structure, map context, check for drift, review quotas, and create local usage receipts.

It helps reveal what information and capabilities Codex can see, distinguish measured results from estimates, and detect changes that could affect reproducibility or cost.

ctxwise — Skill for Codex by FramY2

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.

Any agent

npx skills add FramY2/ctxwise --skill ctxwise

Clone the repo

git clone --depth 1 https://github.com/FramY2/ctxwise

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/framy2/ctxwise/ctxwise/github.svg)](https://agentmods.dev/skills/framy2/ctxwise/ctxwise)

Your own site

<a href="https://agentmods.dev/skills/framy2/ctxwise/ctxwise"><img src="https://agentmods.dev/badge/skills/framy2/ctxwise/ctxwise/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/framy2/ctxwise/ctxwise"><img src="https://agentmods.dev/badge/skills/framy2/ctxwise/ctxwise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 818 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00092	$0.00818
Opus 5.5	$0.00037	$0.00327
Sonnet 5.5	$0.00018	$0.00164
Haiku 4.5	$0.00009	$0.00082

Measured 2d ago against content hash 419eebf6332a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ctxwise 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.

plugins/ctxwise/skills/ctxwise/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CtxWise

Use the installed ctxwise CLI. Keep diagnostics local and distinguish exact, estimated, and unknown measurements.

Workflow

Run ctxwise doctor when availability is uncertain.
Select the narrowest command:
- ctxwise agents for multi-agent context startup tokens and parity across Claude Code (CLAUDE.md), OpenAI Codex (AGENTS.md), and Cursor.
- ctxwise sync --compress to synchronize AGENTS.md ↔ CLAUDE.md ↔ .cursor/rules with deterministic Token Diet compression.
- ctxwise mcp-xray --probe-stdio to rank MCP server tool schemas by token weight and spot bloated schemas.
- ctxwise shield --fail-on-risk to scan context files and skills for leaked API keys, prompt injection, and hidden Unicode.
- ctxwise preset to list or apply curated stack budgets and guidance templates.
- ctxwise snapshot for an immediate ranked context health check and safe next actions.
- ctxwise budget --max-known-tokens 4000 to check an explicit estimated context threshold; add --fail-on-exceed only for an intentional CI gate.
- ctxwise audit --json for config, guidance, skills, agents, and MCP inventory.
- ctxwise map --out ctxwise-context.mmd for a local visual context map.
- ctxwise xray <prompt-input.json> --json for a privacy-safe prompt breakdown.
- ctxwise profile <policy.yaml> --dry-run before staging or installing profiles.
- ctxwise lock for a redacted, hash-based reproducibility manifest.
- ctxwise drift --fail-on-drift to detect unreviewed context changes locally or in CI.
- ctxwise quota --json for the current local plan and rate-limit snapshot.
- ctxwise run --receipt --prompt-xray "<prompt>" for a final-answer receipt with an estimated pre-turn prompt size.
Explain findings before changing configuration.
Use ctxwise profile ... --install only when the user explicitly requests the install; report the backup path.

Cost rules

API-key mode may show a dated token-based charge estimate.
ChatGPT subscription mode shows tokens, credit equivalent, and quota when available. Do not call included usage a dollar charge.
Add --api-equivalent only when the user asks for the comparison. Preserve the label comparison only; not charged.
Keep missing values as unknown; never replace them with zero.
Treat budget totals as estimated known startup context, not an exact context window. Use unknown: fail only when unmeasured surfaces must block CI.
Keep aggregate turn input separate from prompt-window occupancy.
Do not claim savings without a comparable, quality-passing baseline.

Read the full file on GitHub · 58 lines

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.

agents/openai.yaml 245 B

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.

2d ago Changed · +5 lines 419eebf6332a
19d ago Changed · +4 lines · +8 tokens per session 81cf31a53875
1mo ago First seen · 49 lines · 84 tokens per session scan A 0752483c2ecf

Subscribe to this mod's changes

ctxwise is a skill published in the GitHub repository FramY2/ctxwise (7 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 818 once invoked, about $0.0004 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 2026-08-31.

Building agents Memory and context codex codex-cli context-window developer-tools local-first openai

boss-briefing

Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.

sehoon787/my-codex · 23 tokens

briefing-vault

Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.

sehoon787/my-codex · 28 tokens

compact-kb

Use only when user explicitly invokes $compact-kb.

breezewish/CodexPotter · 15 tokens

maintain-codex-wiki

Maintain a review-first Markdown knowledge base for Codex practices with source provenance, engineering capture, citation-aware queries, explicit archive and promotion, and deterministic linting. Use when asked to capture a durable engineering lesson, ingest Codex research, query or archive what the repository knows…

Phelan164/codex-howto · 76 tokens

recap

Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.

M-T-D-N/agentmemory-codex-windows · 58 tokens

productivity-memory

Two-tier memory system that makes the AI a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so the AI understands requests like a colleague would. Uses CONTEXT.md for working memory and a memory/ directory for the full knowledge base.

frumu-ai/tandem · 58 tokens