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 | $0.00144 | $0.04201 |
| Opus 5.5 | $0.00058 | $0.01680 |
| Sonnet 5.5 | $0.00029 | $0.00840 |
| Haiku 4.5 | $0.00014 | $0.00420 |
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 13d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stacked PRs
Build, publish, synchronize and validate stacked pull requests without corrupting branch topology, and decide the topology, provenance and native membership that landing an existing stack depends on.
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.
Landing, post-landing promotion and retargeting, and cleanup of an existing manual or GitHub-native stack have one executable owner: the ship-workflow skill's stack graph run. This skill authors its explicit stack decision packet and delegates to it once (§5); it has no hand-run landing or cleanup procedure of its own.
Reference Files
| File | Contents | Load When |
|---|---|---|
references/stack-model.md |
Stack inference, explicit ordering, native detection and the explicit stack decision packet | Inspecting, publishing, validating, or delegating a stack |
references/provider-adapters.md |
Provider adapter contract and GitHub gh commands for listing, creating, retargeting and checking PRs |
Creating, retargeting or checking PRs |
references/sync-algorithm.md |
Slice proof, expected-old leases and the standalone restack procedure | Syncing a stack after a parent or base moves |
references/merge-discipline.md |
Parent-first landing rules, landing proofs, retention and endpoints the delegated run enforces | Deciding what to select and what an outcome means |
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 choosing a merge method |
references/github-native.md |
Native detection, linking eligibility, native sync and the native prefix policy | A GitHub-native stack is requested or detected |
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.
- 13d ago Changed · +2 lines f994106c19bd
- 14d ago Changed · -114 lines · +22 tokens per session 97366a7e02ff
- 1mo 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 (337 stars, last pushed 2d ago), licensed MIT. It adds 144 tokens to every session and 4,201 once invoked, about $0.0006 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 2026-09-05.
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…
gh-pr-review
Review GitHub Pull Requests using the gh CLI. Use when a user asks to review a PR, perform code review, check a pull request, or provide feedback on proposed changes. Triggers on phrases like "review PR", "review pull request", "check PR", "code review".
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…
mx-pr
Draft a pull request from the feature spec and git log, 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].
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.