A finalization workflow for a completed /run-epic or /fix-tickets batch. An epic is a larger tracked piece of work that groups related tickets; the workflow merges the work, cleans temporary worktrees, closes the epic when appropriate, and reports what remains.

Use it only after completing an epic or ticket-fixing batch, and only by typing /wrap-epic. It helps identify the relevant branch and epic, merge the integration work, remove temporary worktrees, and record the final status.

It gathers the cleanup and handoff steps needed after a batch of changes is finished. It also requires confirmation before performing its destructive operations.

wrap-epic — Skill by phobologic

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.

agentmods

npx agentmods add skills/phobologic/claude_code_helpers/wrap-epic

Any agent

npx skills add phobologic/claude_code_helpers --skill wrap-epic

Clone the repo

git clone --depth 1 https://github.com/phobologic/claude_code_helpers

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,534 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00056	$0.01534
Opus 5	$0.00028	$0.00767
Sonnet 5	$0.00011	$0.00307
Haiku 4.5	$0.00006	$0.00153

Measured 2d ago against content hash 24e9dcf17aee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wrap-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 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.

skills/wrap-epic/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrap Epic

Finalize a completed /run-epic or /fix-tickets run. The skill merges the integration branch into main, cleans up ephemeral state, closes the epic if appropriate, and leaves the user with a clear picture of what remains.

This skill performs destructive operations. Always present the plan and ask for explicit confirmation before executing anything.

Phase 1 — Identify the epic and integration branch

Determine the epic and branch from arguments or the current branch:

If $ARGUMENTS contains an epic ID, use it. Otherwise, read the current branch with git branch --show-current.
Branch naming conventions:
- /run-epic produces epic/<epic-id>
- /fix-tickets produces fix/batch-<timestamp> with a batch epic whose ID is stored as the parent of its child tickets
If the user gave an epic ID, derive the branch:
- Try epic/<id> first
- If not found, search for a recent fix/batch-* branch whose tickets share that epic as parent
If neither the argument nor the current branch resolves, stop and ask the user which epic they want to wrap.

Once resolved, look up:

Epic ticket (tk show <epic-id>) — title, parent, any open child tickets
Integration branch commit range vs main (git log main..<branch> --oneline)
Open findings: children of the epic with status open or in-progress
Worktrees to clean: git worktree list filtered to paths under .worktrees/ that belong to this run (implementer-, fix-batch- matching the branch stamp)

Phase 2 — Present the plan and ask for confirmation

Show a single, structured plan before taking any action. Use this exact shape:

Wrapping epic <id>: <title>

Will do:
  1. Merge <branch> → main           (N commits, M files)            [destructive]
  2. Delete local branch <branch>                                     [destructive]
  3. Prune worktrees:
       .worktrees/implementer-1-...
       .worktrees/implementer-2-...
  4. Close epic <id> with a ship note
  5. Report sub-epic status under <parent-id> (if present)

Will NOT do:
  - Push to remote (you push manually)
  - Delete the remote branch
  - Run tests or /multi-review

⚠ Open review findings still parented under this epic:
     pbp-abcd  P1  "Fix null deref in login handler"
     pbp-efgh  P2  "Add retry to webhook sender"
  You can merge anyway, defer the fixes, or stop and fix first.

Proceed? (yes / yes but skip merge / no)

Read the full file on GitHub · 148 lines

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.

2d ago First seen · 148 lines · 56 tokens per session scan A 24e9dcf17aee

Subscribe to this mod's changes

wrap-epic is a skill published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 1,534 once invoked, about $0.0003 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.

Git and workflow Project management Releases

git-workflow-and-versioning

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…

addyosmani/agent-skills · 74 tokens

release

Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.

openai/symphony · 42 tokens

release-notes

Draft concise release notes.

ollama/ollama · 9 tokens

greptimedb-release

Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).

GreptimeTeam/greptimedb · 75 tokens

refresh-arm-sdk-release

WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…

Azure/azure-sdk-for-net · 91 tokens

store-update

在 CCX Desktop 发布后下载 Store MSIX 并生成发布公告。用户提到 Store 上架、MSIX、从 GitHub Release 下载 store.msix、发布后同步 Windows Store、从 release 填写商店更新内容时必须使用此技能。该技能会下载最新 GitHub Release 的 amd64/arm64 MSIX，校验 sha256，从 Release body 生成 Store listing releaseNotes 预览，并输出手动上传指引。.

BenedictKing/ccx · 100 tokens