Borrowing it
Nothing to install: this file belongs to delightful-ai/beads-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/delightful-ai/beads-rs/main/.claude/skills/execute-epic/SKILL.mdgit clone --depth 1 https://github.com/delightful-ai/beads-rsWrote 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/delightful-ai/beads-rs/execute-epic)<a href="https://agentmods.dev/skills/delightful-ai/beads-rs/execute-epic"><img src="https://agentmods.dev/badge/skills/delightful-ai/beads-rs/execute-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.
<a href="https://agentmods.dev/skills/delightful-ai/beads-rs/execute-epic"><img src="https://agentmods.dev/badge/skills/delightful-ai/beads-rs/execute-epic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00912 |
| Opus 5.5 | $0.00020 | $0.00365 |
| Sonnet 5.5 | $0.00010 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
execute-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 2mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Epic Bead
Claim and complete ONE bead from a specified epic, then stop.
Arguments
/execute-epic <epic-id> - The epic to pull the next bead from (e.g., bd-qz97)
Phase 1: Orient
Before claiming, understand the landscape:
bd prime # full workflow state
bd ready # what's available
jj log --limit 20 # recent work
Filter to the epic:
bd show <epic-id> # understand the epic
bd list --parent=<epic-id> # beads in this epic
Before writing new types, traits, errors, or tests, read the relevant doc in docs/philosophy/:
type_design.md- typestate, parse-don't-validateerror_design.md- error context, propagationtrait_design.md- trait boundaries, coherencetest_design.md- test structure, property-based testing
Before writing code, read the essay in docs/philosophy/scatter.md .
Phase 2: Decide
Pick the next bead from the epic. Justify:
- Why this one matters now
- What it unblocks
- Why higher priority than alternatives
Then proceed immediately to execution.
Phase 3: Execute
bd show <bead-id> # understand it fully
bd claim <bead-id> # own it
JJ Rhythm
jj is not git. No staging area - working copy IS the commit.
The loop (runs MANY times per bead):
jj new
# edit ONE thing (add a fn, write a test, fix a bug)
jj describe "<bead-id>: what you did"
# repeat
Heuristics:
- ~50 lines changed without describe? Too much.
- About to run cargo check/test? Describe first.
- Did two unrelated things? Should've been two commits. Use
jj split.
Every commit message includes the bead ID. 3-15 commits per bead is normal. 1 commit = batched too much.
Handling Uncommitted Changes
If there are uncommitted changes when you start:
- They're probably from your previous work in this session
jj describethem with what they actually are- Or if genuinely unclear, ask the user what they are
- Do NOT create fake "wip: pre-existing" commits
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.
- 2mo ago First seen · 136 lines · 50 tokens per session scan A 779d7f2fb2bc
execute-epic is a skill published in the GitHub repository delightful-ai/beads-rs (24 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 912 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
execute-epic compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| execute-epicdelightful-ai/beads-rs | Skill | 24 | 2mo ago | MIT | A | 50 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 20 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 51 | Claude Code |
| comet-githubrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 72 | Claude Code, Codex |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |