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 skills add Xakki/ai-agents-skills --skill epic-leadgit clone --depth 1 https://github.com/Xakki/ai-agents-skillsWrote 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/xakki/ai-agents-skills/epic-lead)<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/epic-lead"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/epic-lead/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/epic-lead"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/epic-lead.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00024 | $0.01149 |
| Opus 5 | $0.00012 | $0.00575 |
| Sonnet 5 | $0.00005 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
epic-lead 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic lead
The epic-lead is the single team-lead for one approved EPIC. It owns the whole EPIC end-to-end — scope, dependencies, delegation, review, integration, and authorized finalization — and delegates the implementation to sub-agents. It does not implement in the main thread.
This skill is runtime-agnostic: it works for any agent application that can delegate sub-agent work. Adapt the concrete delegation and ask mechanism to your runtime; the orchestration rules below are universal.
Before acting, load and follow ai-agents-skills:kanban,
ai-agents-skills:git-flow, and ai-agents-skills:teamlead. They own the
Kanban lifecycle/scripts, Git mechanics, and delegation/review rules. This skill
adds only the EPIC orchestration delta.
Scope
- Own exactly one named
EPIC-<NUM>and its approved child cards. There is no separate portfolio lead: this role makes the scope, dependency, and escalation decisions for its own EPIC. Do not start another EPIC, infer a new card, or expand scope. - Record a short decision digest in the parent card before mutation: EPIC ID, approved children, dependencies, acceptance criteria, authorization form, default-branch baseline SHA, and parked risks.
- Accepted finalization authorization is explicit user approval at hand-off or recorded EPIC-scoped upfront autonomous authorization. The latter applies only to the named EPIC and approved children; it never grants push, later-EPIC startup, scope expansion, or a test/review bypass.
Prepare
- Detect the default branch; never assume
main. On it, require a cleangit status --shortbaseline and record its SHA. Pre-existing dirt blocks this EPIC procedure until resolved. - Create exactly one
epic/<ID>branch from that baseline. All child work stays on this branch; use Kanban's epic/subtask IDs and scripts. - Agree the sub-agent model and reasoning level before starting. Ask the
user one question (options + a recommendation) to set the model tier and
reasoning level for the sub-agents that will implement the children. Use the
ai-agents-skills:model-tiersmapping (cheap / standard / judgment) and pass the resolved slug on every delegation. If the user has no preference, default to standard and let a sub-agent escalate on ambiguity. - Build one concise dependency, acceptance, and evidence matrix. For each child record predecessors, owner/zone, allowed paths, scoped gate, integration boundary, and acceptance evidence.
- Parallel work is allowed only when the parent card declares it, dependencies permit it, and zones/allowed paths do not overlap. Otherwise follow listed child order.
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.
- 11d ago First seen · 96 lines · 24 tokens per session scan A 4a01290d148c
epic-lead is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 20d ago), licensed MIT. It adds 24 tokens to every session and 1,149 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
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
specs
Use when a rough user story, bug report, feature idea, piece of feedback, or an implementation plan should be recorded as a GitHub issue — "file a ticket for this", "open an issue", "write this up for the backlog", "we should track this", "log this bug", "spec this out as a ticket so we can pick it up later" — i.e.…
ag-pipeline-issue
Pipeline Issue→SPEC→Build→Verify→Test. Toda GitHub Issue gera SPEC antes de implementar, e toda implementacao e verificada contra a SPEC e testada. Use when starting work on a GitHub Issue.
ag-team-terminais
Protocolo para 2+ sessoes Claude interativas em terminais separados trabalharem no MESMO repo com objetivos distintos. Coordenador + workers, manifesto duravel em docs/ai-state/team/, mensagens nativas via ListAgents/SendMessage, worktree por worker. Modos: init | join | status | fechar. Para teammates dentro de UMA…
ag-registrar-issue
Registra GitHub Issues para problemas nao resolvidos imediatamente. Recebe contexto via SendMessage de outros agents. Dedup, labels, severidade. Use when an agent finds a problem it cannot fix now.
ag-teleportar
Switch rapido entre projetos no workspace com contexto preservado. Carrega CLAUDE.md, detecta stack, verifica .env, mostra branch atual, e resume estado. Nao e cd — e context-aware switching.