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/zts0hg/codexspec/codexspec-distillnpx skills add Zts0hg/codexspec --skill codexspec-distillgit clone --depth 1 https://github.com/Zts0hg/codexspecWrote 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/zts0hg/codexspec/codexspec-distill)<a href="https://agentmods.dev/skills/zts0hg/codexspec/codexspec-distill"><img src="https://agentmods.dev/badge/skills/zts0hg/codexspec/codexspec-distill.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.04979 |
| Opus 5 | $0.00014 | $0.02490 |
| Sonnet 5 | $0.00006 | $0.00996 |
| Haiku 4.5 | $0.00003 | $0.00498 |
Grade A, and why
codexspec:distill 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 yesterday.
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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill
Language Preference
Read .codexspec/config.yml. Two independent language controls apply (each falls back to language.output, then English):
- Interaction language (
language.interaction): language for all conversation with the user — questions, explanations, status messages, andcodexspecCLI terminal output. - Document language (
language.document): language for generated artifact files (the profile records).
Converse in the interaction language and author artifacts in the document language. Apply the project's translation standard to both: translate by meaning (not word-for-word), keep English for terms with no good native equivalent, and write as if originally in that language. Exception: evidence.facts quotes the user's original words verbatim and MUST NOT be translated.
User Input
the text after the $codexspec:distill skill mention
Operating Model
distill extracts the reusable, cross-feature knowledge produced during work and persists it to the project-level store .codexspec/profile/. It runs two ways:
- Auto (primary): embedded in wrap-up commands (
implement-taskson completion,commit-staged,pr), gated byworkflow.auto_distillin.codexspec/config.yml(default enabled; disabled only when explicitly set to the literalfalse). - Near-moment (ambient): driven by the profile block's "capture knowledge as you go" rule, distill may be invoked near the moment reusable cross-feature knowledge is produced — in any session, including plain chat or a non-SDD fix that never reaches a wrap-up command. This is the primary way knowledge from ad-hoc work is captured at all.
- Long-run: in a long-running
implement-tasks, distill along the way near each knowledge-producing event rather than only at the very end, so mid-task evidence is not lost to context compaction; the end-of-taskauto_distillstill runs as a backstop. - Manual (fallback): invoked directly on the supplied or most-recent interaction segment.
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.
- yesterday Changed · +7 tokens per session b0837b24bc7f
- 4d ago First seen · 217 lines · 21 tokens per session scan A e7ae94cada7c
codexspec:distill is a skill published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 4,979 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 2026-08-31.
Other skills, from other repositories
test-assess
Test agentready assess against real GitHub repositories to validate assessor changes. Selects repos relevant to the change being tested, clones them to a temp directory, runs the local checkout's assessor, reports results and output locations, then cleans up. Use when testing a new or modified assessor, verifying a…
implement-type-annotations
Add comprehensive type hints to Python/TypeScript code to improve IDE support, catch errors early, and enable better AI code understanding.
setup-claude-md
Create comprehensive CLAUDE.md files with tech stack, standard commands, repository structure, and boundaries to optimize repositories for AI-assisted development.
python-anti-patterns
Use this skill when reviewing Python code for common anti-patterns to avoid. Use as a checklist when reviewing code, before finalizing implementations, or when debugging issues that might stem from known bad practices.
python-background-jobs
Python background job patterns including task queues, workers, and event-driven architecture. Use when implementing async task processing, job queues, long-running operations, or decoupling work from request/response cycles.
python-design-patterns
Python design patterns including KISS, Separation of Concerns, Single Responsibility, and composition over inheritance. Use this skill when designing a new service or component from scratch and choosing how to layer responsibilities, when refactoring a God class or monolithic function that has grown too large, when…