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 HigorAlves/orc --skill stack-prgit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/stack-pr)<a href="https://agentmods.dev/skills/higoralves/orc/stack-pr"><img src="https://agentmods.dev/badge/skills/higoralves/orc/stack-pr/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/higoralves/orc/stack-pr"><img src="https://agentmods.dev/badge/skills/higoralves/orc/stack-pr.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 | $0.00053 | $0.02906 |
| Opus 5.5 | $0.00021 | $0.01162 |
| Sonnet 5.5 | $0.00011 | $0.00581 |
| Haiku 4.5 | $0.00005 | $0.00291 |
Grade A, and why
stack-pr 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.
How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stack PR
Overview
A stack is N chained PRs where each branch's base is the previous branch (not main). Reviewers approve incrementally, merging bottom-up. orc supports two construction strategies and one tool integration:
- Strategy A — commit-based (default) — every commit on the branch becomes one PR. Requires clean Conventional Commits.
- Strategy B — smart (
--smart) — an analyzer agent reads the diff, proposes logical slices, and emits a non-interactive rebase plan. Higher risk, requires backup branch. - Tooling —
github/gh-stackghextension if installed; otherwise a plain-ghfallback that does the same chaining manually.
Announce at start: "I'm using the stack-pr skill to construct a stacked PR group."
Preconditions (both strategies)
- Tests pass — invoke
orc:verification-before-completionfirst. - Clean working tree —
git status --porcelainmust be empty. - No merge commits on
base..HEAD—git rev-list --merges base..HEADmust be empty. Stacks fall apart through merges. - At least 2 commits on
base..HEAD. A single commit isn't a stack — use/orc:ship. - Branch is pushed-clean — local matches
origin(no unpushed work the rebase could lose).
If any precondition fails, surface a ⚠️ Caution callout naming the failed precondition and stop. Don't try to "fix it for them" — these are user decisions.
Strategy A — commit-based (default)
Validate Conventional Commits
Each commit subject MUST match:
^(feat|fix|refactor|chore|test|docs|perf|build|ci|style)(\([^)]+\))?!?: .+
If any commit fails the regex, surface the offenders and AskUserQuestion:
- Reword via reword-only rebase — non-interactive (
GIT_SEQUENCE_EDITORwrites a todo ofrewordlines; user is prompted for each subject one by one outside the rebase). - Switch to
--smart— the analyzer agent doesn't care about commit subjects; it works from the diff. - Cancel.
Build the stack
What ships with it
1 file 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 Changed 1e494780d837
- 17d ago Changed dada46974022
- 1mo ago First seen · 296 lines · 53 tokens per session scan A f7bc919f85a7
stack-pr is a skill published in the GitHub repository HigorAlves/orc (6 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 2,906 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 2026-09-03.
Other skills, from other repositories
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
review-pr
Perform a comprehensive code review of a pull request.
pr
Analyze changes, detect scope issues, and create a well-structured PR.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…