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 agentmods add skills/framy2/ctxwise/ctxwisenpx skills add FramY2/ctxwise --skill ctxwisegit clone --depth 1 https://github.com/FramY2/ctxwiseWhat 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 | $0.00084 | $0.00585 |
| Opus 5 | $0.00042 | $0.00293 |
| Sonnet 5 | $0.00017 | $0.00117 |
| Haiku 4.5 | $0.00008 | $0.00059 |
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.
How it starts
The opening of the file, as written. The whole thing — 49 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 doctorwhen availability is uncertain. - Select the narrowest command:
ctxwise snapshotfor an immediate ranked context health check and safe next actions.ctxwise audit --jsonfor config, guidance, skills, agents, and MCP inventory.ctxwise map --out ctxwise-context.mmdfor a local visual context map.ctxwise xray <prompt-input.json> --jsonfor a privacy-safe prompt breakdown.ctxwise profile <policy.yaml> --dry-runbefore staging or installing profiles.ctxwise lockfor a redacted, hash-based reproducibility manifest.ctxwise drift --fail-on-driftto detect unreviewed context changes locally or in CI.ctxwise quota --jsonfor 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 ... --installonly 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-equivalentonly when the user asks for the comparison. Preserve the labelcomparison only; not charged. - Keep missing values as
unknown; never replace them with zero. - Keep aggregate turn input separate from prompt-window occupancy.
- Do not claim savings without a comparable, quality-passing baseline.
Safety and privacy
- Do not read Codex session transcripts unless the user supplies a specific file.
- Do not print config values, credentials, cookies, or environment secrets.
- Do not relay authentication or attempt to bypass ChatGPT limits.
- Prefer dry-run and staged output. Inspect generated TOML before installation.
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.
- 2d ago First seen · 49 lines · 84 tokens per session scan A 0752483c2ecf
ctxwise is a skill published in the GitHub repository FramY2/ctxwise (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 84 tokens to every session and 585 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
loop
Use only when user explicitly invokes $loop.
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
vc-agent-teams
Coordinate durable or cross-process work with local JSON mailboxes and vc teams commands. Use when messages must persist beyond one Codex session; prefer built-in Codex subagents for normal in-session delegation.
orchestrate-engineering
Coordinate complex engineering work across bounded subagents while protecting the main context, preventing edit conflicts, and measuring whether delegation was worthwhile. Use when the user asks to delegate, parallelize, orchestrate, use subagents, fan out a review, or handle a large task with independent workstreams…
choose-engineering-flow
Select the smallest useful Codex engineering workflow from this repository's existing skills. Use when a task spans multiple engineering concerns, the user is unsure which skill to invoke, or loading every specialist would waste context; return a recommendation only and do not execute the engineering task.
skill-installer
Install Codex skills into $CODEXHOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).