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 jscraik/Agent-Skills --skill keep-codex-fastgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/keep-codex-fast)<a href="https://agentmods.dev/skills/jscraik/agent-skills/keep-codex-fast"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/keep-codex-fast/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/jscraik/agent-skills/keep-codex-fast"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/keep-codex-fast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 35 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 48 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 133 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00047 | $0.02189 |
| Opus 5.5 | $0.00019 | $0.00876 |
| Sonnet 5.5 | $0.00009 | $0.00438 |
| Haiku 4.5 | $0.00005 | $0.00219 |
Grade A, and why
keep-codex-fast 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keep Codex Fast
Philosophy
- Diagnose before cleanup; the first pass is evidence, not mutation.
- Preserve continuity before reclaiming space; old chats are work history until a handoff exists.
- Treat
~/.codexas live control-plane state: backup first, require explicit mutation confirmation, and leave restore evidence behind. - Use Harness Engineering language: current state, evidence, decision, action, verification, handoff.
When To Use
- Codex Desktop or CLI feels slower after many long-running chats.
- The user wants safe inspection, backup, archival planning, or handoff-first chat retirement for Codex local state.
- A recurring Codex maintenance reminder is requested, with report-only behavior.
Avoid
- Automatic cleanup without a fresh report.
- Mutation while Codex is running or process detection cannot prove it is safe.
- Deleting chats, worktrees, logs, skills, plugins, memories, rules, or automations.
- Rewriting
config.tomlfrom broad heuristics without explicit prune confirmation.
Inputs
- Codex home, defaulting to
CODEX_HOMEor~/.codex. - Intent: report, backup-only, apply archive actions, create a handoff, or create a report-only reminder.
- Age thresholds, exact apply confirmation, and optional details mode for raw IDs, titles, paths, and process paths.
Outputs
- Local-state report with candidate counts and sizes.
- Backup path when artifacts are written.
- Mutation plan before apply.
- Validation evidence after apply.
- Restore manifest paths when sessions or worktrees move.
- Schema-bound outputs include
schema_version.
Decision Gates
- Fail fast: stop at the first failed gate and do not proceed.
report: read-only default; safe without confirmation; no writes.backup: writes backup artifacts only; no moves, log rotation, or config rewrite.apply: allowed only after this thread reviews a report and the user confirms the exact Codex home.handoff: create durable notes before archiving chats that may still carry active work.automation: report-only reminder; never scheduleapply, backup, config pruning, moves, or log rotation.
What ships with it
15 files 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 181 B
- Infrastructure/references/evals.yaml 3.2 KB
- Infrastructure/references/task-profile.json 1.4 KB
- references/contract.yaml 1.2 KB
- references/evals.yaml 5.5 KB
- references/handoff-template.md 592 B
- references/source-review.md 687 B
- references/task-profile.json 1.4 KB
- scripts/keep_codex_fast_classify.py 2.2 KB runs code
- scripts/keep_codex_fast_report.py 4.1 KB runs code
- scripts/keep_codex_fast_scan_model.py 3.4 KB runs code
- scripts/keep_codex_fast_scan_walk.py 1.2 KB runs code
- scripts/keep_codex_fast_scan.py 1.5 KB runs code
- scripts/keep_codex_fast.py 368 B runs code
- tests/test_keep_codex_fast.py 384 B runs code
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 First seen · 167 lines · 47 tokens per session scan A 6e8794ead19e
keep-codex-fast is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 2,189 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
terminal-ops
Evidence-first repo execution workflow for ECC. Use when the user wants a command run, a repo checked, a CI failure debugged, or a narrow fix pushed with exact proof of what was executed and verified.
RootCauseAnalysis
Structured incident investigation using Five Whys, Fishbone, blameless Postmortem, Fault Tree, Kepner-Tregoe, and FMEA — traces failures to systemic root causes rather than blaming humans. USE WHEN root cause, RCA, 5 whys, fishbone, postmortem, incident analysis, fault tree, why does this keep failing, blameless…
Vitals
Read-only macOS performance inspection: a deterministic CLI gathers the numbers, Interpretation.md turns them into a diagnosis instead of a data dump.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…