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/jovandyaz/knowtis-app/stacking-prsnpx skills add jovandyaz/knowtis-app --skill stacking-prsgit clone --depth 1 https://github.com/jovandyaz/knowtis-appWrote 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/jovandyaz/knowtis-app/stacking-prs)<a href="https://agentmods.dev/skills/jovandyaz/knowtis-app/stacking-prs"><img src="https://agentmods.dev/badge/skills/jovandyaz/knowtis-app/stacking-prs.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.00601 |
| Opus 5 | $0.00034 | $0.00300 |
| Sonnet 5 | $0.00014 | $0.00120 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
stacking-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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stacking PRs (GitHub + CodeRabbit)
Knowtis uses GitHub's gh-stack extension for stacked PRs and CodeRabbit for automated first-pass review.
Workflow
- Branch with a Conventional prefix:
feat/<name>,fix/<name>,docs/<name>. - Install the extension once with
gh extension install github/gh-stackifgh stackis unavailable. - Build a tracked stack with
gh stack init <bottom-branch>,gh stack add <next-branch>, andgh stack submit --auto --open, or adopt existing PRs withgh stack link <bottom> … <top>.linktakes PRs or branches bottom-first, creates no local tracking, and only adds membership. - Keep every PR under 100 changed files; CodeRabbit refuses larger reviews. Check with
git diff --name-only <base> <head> | wc -lbefore opening. - Trigger CodeRabbit with
@coderabbitai full reviewand confirm inline comments exist. A green check without comments can mean the review was skipped; fair-usage failures must be retried after the named window. - Address all review feedback before human review.
- Merge with an explicit target, for example
gh stack merge <pr-number> --yes, then rungh stack synclocally. Never manually rebase a stacked branch after GitHub merges and retargets a layer. - Detailed context lives in the PR description; commits stay single-line.
Gotchas
gh stack viewneeds local tracking; afterlink, rungh stack checkout <stack-number>first.gh pr editis broken on this repo (deprecated GraphQL field). Change bases and bodies withgh api repos/<owner>/<repo>/pulls/<n> -X PATCH --input -.- Deleting a branch that is the base of an open PR auto-closes that PR, and GitHub then refuses both a base change and a reopen. Run
gh pr list --base <branch>before deleting anything. - Verify
gh auth statusshows the intended account before every write.
Rules of thumb
- A PR that mixes a refactor with a behavior change should be split into a stack (refactor below, behavior on top).
- Do not merge a middle layer independently; use the stack-aware merge flow.
- CI must be green per-PR;
nx affectedkeeps each stack level cheap.
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.
- 5d ago First seen · 34 lines · 68 tokens per session scan A 8850812c52e3
stacking-prs is a skill published in the GitHub repository jovandyaz/knowtis-app (3 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 601 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts) and an annotated tag. Verify, commit, tag. Stops at "committed and tagged locally" — no push, no publish. The release-and-publish skill picks up from here. Distilled…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…
save
Use when the user says 'push my work', 'save everything', or 'commit and push' — pushes the working branch and opens a PR to develop. Not when the user is leaving/done (/handoff, which auto-saves).
release-extensions
Publish or cut a release of the five @docs.plus/extension- packages — package contract, release-family flow, OTP publish, version doctrine, preflight gates, and CHANGELOG style. Use when publishing, cutting a release, bumping an extension version, or preparing a CHANGELOG for npm.
kiln-prerelease-check
Run the Kiln pre-release smoke test suite plus the standard CI checks (checks.sh), diagnose every prerelease test that broke (and why), and write a clean readable report with recommended actions. Read-only — it never edits code. Use when the user wants to validate a release candidate, run prerelease tests, or asks for…
release-digest
Post a "what's changed since the last release" recap to the release Slack channel for final QA. Groups merged PRs by author and classifies each as feature / bug fix / task. Use when the user wants a release recap, a changelog since the last tag, or to prep QA before cutting a release from main.