Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Mathews-Tom/armorynpx agentmods add skills/mathews-tom/armory/stacked-prsWrote 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/mathews-tom/armory/stacked-prs)<a href="https://agentmods.dev/skills/mathews-tom/armory/stacked-prs"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/stacked-prs/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/mathews-tom/armory/stacked-prs"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/stacked-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 47 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 162 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 243 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00122 | $0.04381 |
| Opus 5 | $0.00061 | $0.02191 |
| Sonnet 5 | $0.00024 | $0.00876 |
| Haiku 4.5 | $0.00012 | $0.00438 |
Grade A, and why
stacked-prs 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stacked PRs
Build, publish, synchronize, validate, merge, and clean up stacked pull requests without corrupting branch topology.
The package identity is provider-neutral. Git is the source of truth for branch ancestry; provider PR metadata is the source of truth for review bases. GitHub through gh is the first documented provider adapter.
Reference Files
| File | Contents | Load When |
|---|---|---|
references/stack-model.md |
Stack inference, explicit ordering, and .stack-prs.yaml rules |
Inspecting, publishing, validating, or cleaning a stack |
references/provider-adapters.md |
Provider adapter contract and GitHub gh commands |
Creating, retargeting, checking, merging, or deleting PRs |
references/sync-algorithm.md |
Rebase and force-with-lease synchronization workflow | Syncing a stack after a parent or base moves |
references/merge-discipline.md |
Bottom-up merge and branch cleanup rules | Merging or closing out a stack |
references/metadata-format.md |
Optional metadata schema and validation rules | .stack-prs.yaml exists or inference is ambiguous |
references/provenance.md |
Commit-trailer stack identity, stamping, verification, merge-mode coupling | Creating, splitting, syncing, or merging any stack |
references/github-native.md |
Eligibility, gh stack operations, preview limits, and manual fallback |
A GitHub-native stack is requested or detected |
When To Use
| Use this skill | Use another package |
|---|---|
| Multiple dependent branches need PRs against parent branches | ship-workflow for one independent release PR |
| A feature branch must be split into reviewable dependent branches | task-decomposer for planning tasks before code exists |
| An existing stack needs rebasing, retargeting, validation, or merge sequencing | pr-review for reviewing one PR diff |
| A stack must be cleaned after merge | General Git commands for unrelated branch cleanup |
Core Rules
- Run
git rev-parse --show-toplevelbefore any workflow. - Run
git status --porcelainbefore rebases, pushes, PR creation, PR retargeting, merge, or cleanup. - Stop on a dirty worktree unless the user explicitly scopes the operation to inspection only.
- Prefer existing PR
baseRefNamevalues over inferred ancestry. - Resolve
<base>from the root PR'sbaseRefName(gh pr view <root-pr> --json baseRefName --jq .baseRefName), not fromorigin/HEAD; a stack's trunk need not be the repository's default branch. - Use explicit branch order or
.stack-prs.yamlwhen parent inference is ambiguous. - Never use plain
git push --force; usegit push --force-with-lease origin <branch>. - Merge from root to leaf. Never merge a child before its parent.
- Do not delete unmerged stack branches without explicit user instruction.
- Stamp
Stack-IdandStack-Positiontrailers on every commit the skill creates or splits; copy the ID from.stack-prs.yamlor mint it once when absent. - Verify trailers are present and consistent before merge.
- Probe every open stack PR for native-stack membership during Inspect (
references/stack-model.md§ Native Stack Detection) before merge planning; a detected native stack makes the manual merge path in §5 unavailable, not merely discouraged. - Detect the provider's squash message policy (
squash_merge_commit_message) before merging with--squash. Fold trailers into the squash body only when the policy isPR_BODYorBLANK; underCOMMIT_MESSAGES(GitHub's default) trailers already survive automatically.
What ships with it
8 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.
- 5d ago First seen · 374 lines · 122 tokens per session scan A f6fe0e207ddf
stacked-prs is a skill published in the GitHub repository Mathews-Tom/armory (316 stars, last pushed 4d ago), licensed MIT. It adds 122 tokens to every session and 4,381 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
gh-issues
Use when creating, searching, updating, or managing GitHub issues via CLI. Triggers: "issue", "create issue", "gh issue", "task tracking", "context", "handoff", "resume task", "session context", "save progress", "active tasks", "in-progress", "my tasks", "open issues". Covers: gh commands, bulk operations, JSON/jq…
mx-pr
Draft a pull request from the feature spec and git log, run an autonomous commit-history cleanup (content check), then publish to GitHub or GitLab (Bitbucket experimental) — or hand off. Use when a feature branch is ready for PR, standalone or from mx-flow. Usage: /mx-pr [name].
mx-commit
Commit all pending changes as one commit per logical concern, following the project's message convention (type prefix, 50-char subject, English). Use when the working tree may hold several changes or the convention must be enforced; a single trivial change can use plain git commit. Usage: /mx-commit [--auto].
safe-public-release
Use when publishing, open-sourcing, exporting, sanitizing, or moving code, agent skills, prompts, templates, fixtures, datasets, workshop assets, or other artifacts from a private repository, vendor/runtime environment, or mixed working directory into a public repository or registry. Builds a provenance inventory…
dirty-worktree-discipline
Keeps agent work safe in messy repositories. Use when git status is dirty, unrelated files exist, generated artefacts are present, multiple agents share a repo, or you must commit only the intended slice without damaging someone else's work.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.