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 agents/thuandiep1707/codex-harness-javascript/skillgit clone --depth 1 https://github.com/thuandiep1707/codex-harness-javascriptWhat 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 | $0.00000 | $0.00936 |
| Opus 5 | $0.00000 | $0.00468 |
| Sonnet 5 | $0.00000 | $0.00187 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
skill 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow and capability architecture
Taxonomy
- Workflow: user-facing orchestration entry point. Đây là thứ user gọi bằng
$. - Internal capability: reusable knowledge/workflow fragment của một agent. Không expose bằng
$. - Rule: mandatory behavior/convention.
- Protocol: structured contract giữa controller/agent.
Public workflow discovery
Codex chỉ discover public workflow trong:
.agents/skills/<workflow-name>/SKILL.md
Vì vậy .agents/skills/ phải được giữ nhỏ và chỉ chứa entry point mà user thực sự cần nhìn thấy.
Current public workflows:
frontend-delivery
frontend-planning
Public workflow package:
.agents/skills/<workflow-name>/
├── SKILL.md
└── agents/
└── openai.yaml
agents/openai.yaml chỉ là UI metadata, không cấp execution authority.
Internal capabilities
Knowledge nội bộ nằm ngoài discovery root và dùng CAPABILITY.md thay vì SKILL.md:
.agents/capabilities/
├── common/
└── frontend/
Ví dụ:
.agents/capabilities/common/discover-project-stack/CAPABILITY.md
.agents/capabilities/frontend/plan-frontend-work/CAPABILITY.md
.agents/capabilities/frontend/shadcn/CAPABILITY.md
.agents/capabilities/frontend/testing/CAPABILITY.md
Internal capability package không có agents/openai.yaml, vì nó không phải public Codex entry point và không được user invoke trực tiếp.
Agent manifest dùng internal-capabilities: làm allowlist path. Specialist chỉ load capability khi capability đó vừa nằm trong manifest allowlist vừa được Orchestrator route trong issue-handoff.
Progressive disclosure
Public side:
- Codex discover workflow name/description.
- User hoặc intent routing chọn một workflow.
- Chỉ workflow đó được load.
Internal side:
- Workflow spawn đúng agent.
- Agent đọc manifest/rules.
- Brain detect project stack bằng evidence rẻ khi cần.
- Orchestrator route smallest internal-capability set cho từng Subtask.
- Specialist chỉ load capability được route.
- Capability chỉ load reference cần cho nhánh hiện tại.
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 · 132 lines · 0 tokens per session scan A 8a36f91468aa
skill is an agent published in the GitHub repository thuandiep1707/codex-harness-javascript (7 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 936 tokens. 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 agents, from other repositories
task-specialist
Bounded implementer for one ready task with an exclusive write set and approved context.
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.
ap-framework-generator
L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…
ap-framework-validator
L4 terminal leaf - FRAMEWORK VALIDATE (HRN-5). A fresh, default-FAIL juror that proves a GENERATED framework is SOUND before any gate runs. Checks the HRN-5 default-FAIL checklist - every gate mapped, exactly one terminal DONE with negatives looping UP, the BLOCKED invariant verbatim, a non-empty acceptance set. PASS…
ap-scoper
L3 useful-first roadmap author or complementary scout - proves capability when needed, inspects the real repository, and contributes to one executable ROADMAP.md without spawning.
ap-arbiter
L4 terminal leaf - ARBITER. Independent decision-maker for forks the loop cannot resolve on its own. Under UNATTENDED mode it ALWAYS rules and continues, NEVER escalates to the user. Output is a binding ruling logged to the ledger.