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 jxoesneon/Ciel --skill finishing-a-development-branchgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/finishing-a-development-branch)<a href="https://agentmods.dev/skills/jxoesneon/ciel/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/finishing-a-development-branch/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/jxoesneon/ciel/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/finishing-a-development-branch.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 | $0.00037 | $0.00820 |
| Opus 5 | $0.00018 | $0.00410 |
| Sonnet 5 | $0.00007 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
finishing-a-development-branch 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Finishing a Development Branch (Finality Layer)
This skill formalizes the "Finality Layer" of CIEL orchestration. It is triggered when an implementation plan (managed by executing-plans) is deemed complete. It prevents broken code from entering the main branch by enforcing a hard global verification gate before presenting integration options.
Integration Context
Adapted from ~/.agents/skills/finishing-a-development-branch/. This is the final step in the CIEL lifecycle: brainstorming -> make-plan -> executing-plans (wrapping subagent-driven-development) -> finishing-a-development-branch.
The Finality Workflow
Step 1: The Global Verification Gate (Hard Stop)
Before offering any integration options to the user, the Orchestrator MUST run the full project verification-loop (lint, test, build).
- If Verification Fails: Halt. Present the failures to the user. The branch cannot be merged or PR'd until the build is green.
- If Verification Passes: Proceed to Step 2.
Step 2: Present Integration Options
The Orchestrator MUST present exactly these four options using the ask_user tool (type: choice):
- Create Pull Request: Push the branch and create a PR (e.g., using the
ghCLI). - Merge Locally: Checkout
main/master, pull, merge the feature branch, and delete the local feature branch. - Keep As-Is: Do nothing. Leave the branch and worktree intact.
- Discard: Permanently delete the branch and worktree. (Requires an explicit confirmation step).
Step 3: Evolutionary Retrospective (Post-Mortem)
Before destroying the branch or worktree, the Orchestrator MUST extract actionable lessons from the development cycle to inform future epics:
- Log the success rate, recurring blocker themes, or architectural friction points encountered during implementation to the MemPalace Diary (
mempalace_diary_write). - If new implicit dependencies were discovered, update the Knowledge Graph (
mempalace_kg_add).
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.
- 7d ago First seen · 67 lines · 37 tokens per session scan A c02070e6f6d8
finishing-a-development-branch is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 820 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
branch_health
Quick health check -- test counts and file stats for AIPass branches.
repo-harness-check
Verification entrypoint for repo-harness workflow readiness. Runs workflow gates, task sync, contract checks, inspector, and migration dry-run before merge or release.
review-tests
Reviews test quality and coverage. Use when checking that a diff has adequate tests, checking a new or edited test, or auditing the test suite of a codebase.
testing-rate-limiting
Apply deterministic SlowAPI rate-limiter isolation for FastAPI transport tests, especially to avoid flaky HTTP 429 responses.
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
fluent
Operate the fluent workflow to build software autonomously over extended periods. Interactive stages (brief, behaviors, approach, plan) run with the user. Autonomous execution loops writer → tester → parallel reviewers, then runs the Learner after a passing review round. Only a successful Learner run produces a ready…