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/thuandiep1707/codex-harness-javascript/frontend-planningnpx skills add thuandiep1707/codex-harness-javascript --skill frontend-planninggit clone --depth 1 https://github.com/thuandiep1707/codex-harness-javascriptWrote 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/thuandiep1707/codex-harness-javascript/frontend-planning)<a href="https://agentmods.dev/skills/thuandiep1707/codex-harness-javascript/frontend-planning"><img src="https://agentmods.dev/badge/skills/thuandiep1707/codex-harness-javascript/frontend-planning.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 | $0.00048 | $0.00389 |
| Opus 5 | $0.00024 | $0.00195 |
| Sonnet 5 | $0.00010 | $0.00078 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
frontend-planning 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 5d 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.
What it actually says
Frontend Planning Workflow
This is a user-facing planning-only workflow.
Scope
- Resolve the working product repository and Jira context in the Primary Controller.
- Spawn Brain for requirement analysis and lightweight project-stack discovery when new/replan work requires it; capture the result, then close/verify the Brain child.
- Spawn one Orchestrator child in planning/replanning mode and supply the approved analysis plus Jira context.
- Orchestrator decides the Jira Feature/Task/Subtask operations and returns exact
jira-callcontroller actions; it does not call Jira directly. - Primary Controller executes those Jira calls exactly, returns confirmed results to the same Orchestrator child, and repeats until the Jira work graph is valid.
- Capture the final planning result, then close/verify the Orchestrator child.
- Stop before specialist implementation.
Do not dispatch Design, Test Plan, Coding, or Testing specialists in this workflow.
Planning rules
- Decompose
requirement -> user outcomes -> functional slices -> Tasks -> specialist Subtasks. - Do not split primarily by files, components, hooks, or agent roles.
- Human-facing Jira content must be Vietnamese; technical identifiers remain exact.
- Detect project implementation stack from evidence; detection is not permission to adopt a new dependency.
- Record unresolved technology/architecture decisions instead of defaulting to a library.
- Only the Primary Controller invokes the Jira connector and native child-agent lifecycle APIs. Orchestrator owns planning decisions only.
Output
Return the created/updated Jira hierarchy, dependencies, acceptance boundaries, detected implementation-environment evidence, and unresolved decisions. The workflow ends after planning by design.
What ships with it
1 file 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.
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.
- 5d ago First seen · 34 lines · 48 tokens per session scan A e1259fa09e2a
frontend-planning is a skill published in the GitHub repository thuandiep1707/codex-harness-javascript (7 stars, last pushed 7d ago), licensed MIT. It adds 48 tokens to every session and 389 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
qa
Run scalable, isolated live QA for nac development. The top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this skill using all test…
release
Cut and publish a full stable NAC release after main, release-PR, and publication CI pass. Use when a maintainer asks for a stable version bump, tag, or GitHub Release. Never use for release candidates; NAC RC releases are automated.
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
nac-onboarding
Install and configure Arcee AI nac, get the user into the nac dashboard, and connect their MCP client to nac. Use when a user asks to get started with nac, connect nac to an agent, add MCP servers, or expose nac's MCP server to Claude Code, Codex, OpenCode, or another MCP client.
first-run-discovery
Use when project context is missing, unapproved, stale, or when an existing harness must be adopted before implementation planning.
graph-execution
Use to decompose approved context, dispatch ready task nodes, or execute a task under exclusive ownership.