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/martinffx/atelier/code-pull-requestnpx skills add martinffx/atelier --skill code-pull-requestgit clone --depth 1 https://github.com/martinffx/atelierWhat 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 | $0.00084 | $0.00427 |
| Opus 5 | $0.00042 | $0.00214 |
| Sonnet 5 | $0.00017 | $0.00085 |
| Haiku 4.5 | $0.00008 | $0.00043 |
Grade A, and why
code-pull-request 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.
What it actually says
Pull Request / Merge Request Skill
Create, comment on, and merge GitHub pull requests or GitLab merge requests for the
current branch. Assumes the relevant CLI (gh or glab) is installed and authenticated.
This skill is create/read + write-gated. Every write action (create PR, leave comment, respond to comment, merge) requires explicit human confirmation before running.
Start Here
- Detect the platform and find the current branch's open PR/MR — see references/common.md.
- Pick a workflow:
| Workflow | Reference | Trigger phrases |
|---|---|---|
| Create PR/MR | create-pr.md | "open a PR", "make a PR", "submit for review" |
| Read comments | read-comments.md | "read PR comments", "show MR comments" |
| Leave a comment | leave-comment.md | "leave a comment", "comment on the PR" |
| Respond to a comment | respond-to-comment.md | "respond to a comment", "reply on the PR" |
| Merge PR/MR | merge-pr.md | "merge this PR", "ship it", "merge the MR" |
Both GitHub (gh) and GitLab (glab) are first-class. Every write step pauses for
human approval before running the CLI command.
What ships with it
7 files 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.
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 · 36 lines · 84 tokens per session scan A 95cfe43c86c9
code-pull-request is a skill published in the GitHub repository martinffx/atelier (44 stars, last pushed 23d ago), licensed MIT. It adds 84 tokens to every session and 427 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 2026-08-30.
Other skills, from other repositories
configure-notifications
Configure notification integrations (Telegram, Discord, Slack) via natural language.
autopilot
Full autonomous execution from idea to working code.
deepinit
Deep codebase initialization with hierarchical AGENTS.md documentation.
graph
Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery.
autoresearch
Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior.
ask
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via omc ask, with artifact capture and no raw CLI assembly.