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-implement-tasksnpx skills add Zts0hg/codexspec --skill codexspec-implement-tasksgit clone --depth 1 https://github.com/Zts0hg/codexspecWhat 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 | $0.00031 | $0.04380 |
| Opus 5 | $0.00015 | $0.02190 |
| Sonnet 5 | $0.00006 | $0.00876 |
| Haiku 4.5 | $0.00003 | $0.00438 |
Grade A, and why
codexspec:implement-tasks 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Implementer
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 (requirements/spec/plan/tasks).
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.
Feature Resolution
Resolve the feature in this order:
- Use an explicit path from
the text after the $codexspec:implement-tasks skill mentionwhen it identifies atasks.mdfile or feature directory. - Otherwise match the current branch, which must use the timestamp format, to
.codexspec/specs/<branch>/. - If no unique feature can be resolved, ask the user to select one. Never silently select the latest workspace.
Derive all artifact paths from the selected feature directory. All implementation-side output belongs to that workspace.
Input Documents and Authority
Read:
requirements.mdspec.mddesign.mdplan.mdtasks.md.codexspec/memory/constitution.mdwhen present
Authority order:
- Confirmed entries in
requirements.md spec.md- Constitution and verified repository facts
design.md- Approved
plan.md tasks.md
A legacy feature may have no design.md; when it is absent, proceed with plan.md as the design-and-plan authority.
When requirements.md is absent, use legacy spec-only mode. Treat spec.md as
the temporary highest feature authority and state that fidelity to the original
discussion cannot be verified.
Role
You are an autonomous implementation agent. Your responsibility is to execute all tasks in the task list systematically until completion.
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 · 402 lines · 31 tokens per session scan A d849533524bb
codexspec:implement-tasks is a skill published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 4,380 once invoked, about $0.0002 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
spec-manager
Spec-driven project iteration workflow — L1 PRD → L2 Design → L3 Impl → Agent Task → Deploy, with human review gates at each layer. Pure local markdown storage, no MCP, no network. Use when the user invokes /spec-manager or asks for: new feature/PRD, technical design, implementation spec, agent task, iteration plan…
spec-manager
Spec-driven project iteration workflow — L1 PRD → L2 Design → L3 Impl → Agent Task → Deploy, with human review gates at each layer. Pure local markdown storage, no MCP, no network. Use when the user invokes /spec-manager or asks for: new feature/PRD, technical design, implementation spec, agent task, iteration plan…
spec-manager
Spec-driven project iteration workflow: L1 PRD -> L2 Design -> L3 Impl -> Agent Task, with human review gates at each layer.
comet-native
Comet Native 工作流。当用户明确调用 /comet-native、要求启动或恢复 Native change，或入口路由到 Native 时使用。.
comet-design
Comet Classic 阶段 2 —— 为 change 产出深度技术 Design Doc。.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.