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 yarlson/yarstack --skill plan-delivergit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/plan-deliver)<a href="https://agentmods.dev/skills/yarlson/yarstack/plan-deliver"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/plan-deliver/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/yarlson/yarstack/plan-deliver"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/plan-deliver.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 | $0.00071 | $0.01967 |
| Opus 5.5 | $0.00028 | $0.00787 |
| Sonnet 5.5 | $0.00014 | $0.00393 |
| Haiku 4.5 | $0.00007 | $0.00197 |
Grade A, and why
plan-deliver 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Delivery
Own one approved plan from first read to a ready, green, reviewed pull request. Use the plan as the behavior contract, the repository as the implementation authority, and fresh evidence from the current remote PR head for completion.
Establish authority and completion
Confirm the plan source (the latest approved plan in the conversation or a named file), repository, base branch, requested review systems, and terminal condition. Proceed only when the request authorizes edits, commits, pushes, PR creation and ready-state changes, CI fixes, review replies, and thread resolution.
This skill never merges, deploys, releases, or creates or changes a Jira issue.
Finish only when current evidence proves that:
- one PR implements every in-scope plan deliverable and acceptance criterion;
code-reviewran on the final complete diff, and each verified finding is fixed or recorded with a reason;- the PR is open and ready for review, not a draft;
- the remote PR head matches the validated commit;
- every required check for that head passed or has a neutral result allowed by repository rules;
- each requested automated reviewer completed its review of that head;
- each requested automated review thread has a recorded outcome supported by repository evidence, and each actionable thread is resolved;
- the PR title and body match the final diff and test evidence.
Re-read the instruction files
Read these files in full at the start, and read them again immediately before the first edit, because a long investigation or planning conversation pushes them out of attention:
- the user-level agent instructions, such as
~/.agents/AGENTS.md,~/.codex/AGENTS.md, or~/.claude/CLAUDE.md, whichever exist; - every
AGENTS.mdandCLAUDE.mdthat applies to the repository root and to each directory you will change.
When an instruction file conflicts with the plan, follow the instruction file and record the conflict in the result.
Maintain autonomous progress
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 · +3 lines 127edd817068
- 3d ago First seen · 102 lines · 71 tokens per session scan A c2c8c592a1c6
plan-deliver is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 1,967 once invoked, about $0.0003 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 2026-10-18.
Other skills, from other repositories
owndiff-pre-commit
Audit OwnDiff changes before committing or releasing by checking scope, generated artifacts, private data, documentation accuracy, version consistency, structured files, tests, and the OwnDiff ownership gate. Use when a user asks to verify, clean up, prepare, commit, publish, or release changes in the OwnDiff…
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
gentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
github-workflow
GitHub best practices for pull requests, code reviews, issues, Actions workflows, and repository management.