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/lbk-open/super-spec/ss-cleanupnpx skills add lbk-open/super-spec --skill ss-cleanupgit clone --depth 1 https://github.com/lbk-open/super-specWrote 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/lbk-open/super-spec/ss-cleanup)<a href="https://agentmods.dev/skills/lbk-open/super-spec/ss-cleanup"><img src="https://agentmods.dev/badge/skills/lbk-open/super-spec/ss-cleanup.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 | $0.00083 | $0.01817 |
| Opus 5 | $0.00042 | $0.00908 |
| Sonnet 5 | $0.00017 | $0.00363 |
| Haiku 4.5 | $0.00008 | $0.00182 |
Grade A, and why
ss-cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cleanup After Development
Wrap up finished work: confirm the PR/MR is merged (offer to merge it if it's still open), return to the main checkout on the up-to-date default branch, remove the development branch's worktree if it has one, and delete the spent branch locally and, optionally, on the remote.
Core principle: never delete a branch whose work isn't safely landed. A branch is only safe to delete once its PR/MR is merged, or the user explicitly confirms abandoning unmerged work. The same applies to a dirty worktree — uncommitted changes are only discarded after explicit confirmation.
Inputs
--merge: if the branch's PR/MR is open/draft, merge it without asking first.--delete-remote: also delete the remote branch if it still exists after the merge.--force: skip confirmation before discarding a dirty worktree or deleting an unmerged branch.
Step 0 — Fast exit: nothing to clean up
git fetch origin --prune
CURRENT=$(git branch --show-current)
BASE=$(git remote show origin | grep 'HEAD branch' | awk '{print $NF}')
- Detached HEAD (
CURRENTempty) → stop, report the detached state and ask what to do. CURRENTalready equalsBASE→ there's no development branch to clean up. This is the common case for lite-mode work that never left the default branch. Just rungit pull --ff-only origin $BASEto refresh, report, and exit — no further steps needed.
Step 1 — Detect the PR/MR state
Use the same remote-detection logic as the ss-create-pr skill (inspect git remote get-url origin for github.com vs. gitlab.com) to pick the right CLI:
# GitHub
gh pr list --head "$CURRENT" --state all
gh pr view "$CURRENT"
# GitLab
glab mr list --source-branch "$CURRENT" --state all
glab mr view "$CURRENT"
Classify the result:
| State | Meaning | Next step |
|---|---|---|
| Merged | Already merged | Step 3 (safe to delete) |
| Open / draft | Exists, not merged | Step 2 |
| Closed without merging | — | Step 2 (treat as unmerged) |
| None found | No PR/MR was ever opened | Step 2 (treat as unmerged) |
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 · 128 lines · 83 tokens per session scan A 2e2f7fb2ab46
ss-cleanup is a skill published in the GitHub repository lbk-open/super-spec (1 stars, last pushed 14d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,817 once invoked, about $0.0004 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
phx-deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.