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/skill-cataloggit 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 | $0.00607 |
| Opus 5 | $0.00000 | $0.00303 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
skill-catalog 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow and internal capability catalog
Public workflows
Chỉ các entry point dưới .agents/skills/ được expose cho user qua $.
| Workflow | Responsibility |
|---|---|
frontend-delivery |
Chạy frontend end-to-end từ analysis/Jira đến specialist execution, testing và acceptance |
frontend-planning |
Phân tích + tạo/reconcile Jira work graph rồi dừng trước specialist execution |
Common internal capabilities
| Capability | Owner | Responsibility |
|---|---|---|
discover-project-stack |
Brain | Detect framework/library/testing environment từ source/config evidence mà không tự chọn technology |
Frontend internal capabilities
Brain
| Capability | Responsibility |
|---|---|
analyze-frontend-requirements |
Create resumable analysis/revalidation/final acceptance contracts |
design-frontend-module-boundary |
Decide bounded-context ownership and DDD placement from product evidence |
audit-frontend-supply-chain |
Assess dependency/source adoption risk |
audit-frontend-security |
Assess browser/runtime threat surfaces |
Orchestrator
| Capability | Responsibility |
|---|---|
plan-frontend-work |
Plan/resume/pause Jira-backed Functional Tasks/Subtasks, capability routing, handoff composition, reconciliation |
Design
| Capability | Responsibility |
|---|---|
orchestrate-frontend-design |
Use a connected provider and return traceable design evidence |
Test Plan
| Capability | Responsibility |
|---|---|
plan-frontend-testing |
Convert one bounded handoff into a risk-based test-plan artifact |
Coding
| Capability | Responsibility |
|---|---|
migrate-legacy-frontend-module |
Migrate approved legacy behavior within one bounded Coding Subtask |
integrate-third-party-frontend |
Implement an approved external integration within one bounded Coding Subtask |
nextjs-state-management |
Apply approved state-ownership reasoning when routed |
nextjs-tanstack-query |
Implement explicit approved TanStack Query flows when project evidence supports them |
shadcn |
Work with shadcn primitives/source mechanics only when shadcn is detected/approved and routed |
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 · 78 lines · 0 tokens per session scan A 2ec4cbdc3032
skill-catalog 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 607 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
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.
ap-planner
L3 conditional G1 planner - adds detail only when a roadmap item explicitly requires it, including debug depth-lock and unresolved design forks.