tackle-epic

tackle-epic is a skill for Claude Code, Codex from jtsternberg/claude-plugins. It costs 19 tokens per session (1,184 once invoked), scanned A, original, MIT.

A workflow for completing a software epic, meaning a large piece of work made up of smaller tasks, tracked in Beads. It finds the epic, reviews its child tasks, does the work, and creates a pull request.

In plain words
What is it for?
Use it to locate an epic, understand its tasks, work through them on a branch or the current worktree, and open a pull request when finished.
Why use it?
It gives a repeatable path from an epic’s description to completed implementation and a proposed code change for review.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents; mentions Codex.

Part of the beads-workflow plugin — 4 skills shipped together

Good fit Use it to locate an epic, understand its tasks, work through them on a branch or the current worktree, and open a pull request when finished.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jtsternberg/claude-plugins/tackle-epic
Install

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.

Any agent
npx skills add jtsternberg/claude-plugins --skill tackle-epic
Clone the repo
git clone --depth 1 https://github.com/jtsternberg/claude-plugins

Made for: Claude Code, Codex.

Or install beads-workflow, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for tackle-epic

README.md
[![agentmods](https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/tackle-epic/github.svg)](https://agentmods.dev/skills/jtsternberg/claude-plugins/tackle-epic)
Your own site
<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/tackle-epic"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/tackle-epic/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.

agentmods 80×15 button for tackle-epic

Your own site · 80×15
<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/tackle-epic"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/tackle-epic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.01184
Opus 5 $0.00010 $0.00592
Sonnet 5 $0.00004 $0.00237
Haiku 4.5 $0.00002 $0.00118

Measured 9d ago against content hash 3e38680ea08b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tackle-epic 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 9d 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.

plugins/beads-workflow/skills/tackle-epic/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tackle Epic

You are given an epic identifier and optional flags: $ARGUMENTS

Codex: if the invocation text above is not populated, use the text after the skill name. If it is unavailable, infer the epic identifier and optional flags from the current request.

Parse the arguments:

  • The epic identifier is the first argument (everything before any -- flags)
  • If --here is present, work on the current branch/worktree instead of creating a new one

Step 1: Find the Epic

First, locate the epic in beads:

  1. If the argument looks like an ID (e.g., buddy-cli-98w), run: bd show <epic-id>
  2. If it's a name/search term, run: bd list --type=epic --title="<search-term>" to find matching epics

If no epic is found, report the error and stop.

Step 2: Understand the Epic

Once you have the epic:

  1. Run bd show <epic-id> to get full details
  2. Run bd show <epic-id> --children to see all child tasks
  3. Understand the scope and requirements from the epic description

Step 3: Set Up Working Environment

If --here flag is set: Skip worktree creation, then:

  1. Record the current directory as worktree_path.
  2. Resolve the active branch with branch_name="$(git branch --show-current)".
  3. Stop if branch_name is empty; a detached HEAD cannot be pushed safely by this workflow.
  4. Resolve base_ref from the PR base branch when one exists, otherwise from the repository's default remote branch.

Otherwise (default): Create a worktree for this epic:

  1. Generate a branch name from the epic title/context (lowercase, hyphenated, max 50 chars)
    • Format: feature/<epic-id>-<short-description>
    • Example: feature/buddy-cli-98w-webhook-management
  2. Record that value as branch_name, resolve a concrete worktree_path, and create it: git worktree add "<worktree_path>" -b "$branch_name"
  3. Resolve base_ref from the repository's default remote branch.

For every command in the remaining steps, explicitly use worktree_path as the working directory. Do not rely on shell cd state persisting between tool calls.

Read the full file on GitHub · 129 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 129 lines · 19 tokens per session scan A 3e38680ea08b

Subscribe to this mod's changes

tackle-epic is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 1,184 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.

Related

Other skills, from other repositories