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 amazing-fish/agent-skills --skill execute-github-issue-pr-workflowgit clone --depth 1 https://github.com/amazing-fish/agent-skillsWrote 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/amazing-fish/agent-skills/execute-github-issue-pr-workflow)<a href="https://agentmods.dev/skills/amazing-fish/agent-skills/execute-github-issue-pr-workflow"><img src="https://agentmods.dev/badge/skills/amazing-fish/agent-skills/execute-github-issue-pr-workflow/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/amazing-fish/agent-skills/execute-github-issue-pr-workflow"><img src="https://agentmods.dev/badge/skills/amazing-fish/agent-skills/execute-github-issue-pr-workflow.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 | $0.00101 | $0.03055 |
| Opus 5.5 | $0.00040 | $0.01222 |
| Sonnet 5.5 | $0.00020 | $0.00611 |
| Haiku 4.5 | $0.00010 | $0.00305 |
Grade A, and why
execute-github-issue-pr-workflow 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 today.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute GitHub Issue–PR Workflow
Treat GitHub remote state as authoritative. Preserve unrelated work and never commit directly to the default branch.
Establish scope and mode
- Inspect repository instructions, ownership, default branch, working tree, relevant Issues/PRs, checks, and docs.
- For a user-owned repository, create a ready-for-review PR without extra approval. For external upstreams, work only in the user's fork and obtain approval before creating an upstream Issue, opening a Draft upstream PR, or otherwise contacting maintainers.
- Reuse an existing Issue when it covers the work; otherwise create one before non-trivial implementation where authorized. Keep scope and acceptance criteria bounded.
- Use neutral links such as
Refs #Nunless automatic Issue closure is explicitly authorized. - Use default approval mode unless the user explicitly enables automatic staging mode:
- Default: stop after review and diff evidence; merging requires a later explicit approval for the current PR and exact HEAD, and only then may the next Issue start.
- Automatic staging: a reviewed low-risk PR stays open and unmerged while the next Issue starts. Branch independent follow-ups from the current default branch; stack only genuine dependencies and record their order. Stop for human direction when risk appears, PRs conflict, the vision is complete, or the actionable queue is empty.
Run the optional goal-prompt preflight
The parent workflow owns routing whenever the user invokes this workflow, including when the same request asks to optimize a prompt. The main Agent must not invoke $optimize-prompt as a standalone response or return its paste-ready prompt instead of completing an already authorized workflow. In a workflow-owned preflight, $optimize-prompt is an orchestrated child, and its prompt must not replace the workflow's final delivery.
Use these combination cases as the authorization and routing contract:
| Case | Representative input | Route | Preflight | Original implementation authority | Owning Agent outcome |
|---|---|---|---|---|---|
workflow_optimize_and_proceed |
$execute-github-issue-pr-workflow + bugs + “optimize and proceed” |
workflow/orchestrated_child/independent |
used |
authorized |
continue |
standalone_optimize_only |
$optimize-prompt + the same bugs |
optimizer/standalone/no_child |
not_applicable |
not_authorized |
stop |
workflow_prompt_only |
$execute-github-issue-pr-workflow + “only optimize; do not execute” |
workflow/orchestrated_child/independent |
used |
not_authorized |
stop |
workflow_child_failure |
authorized $execute-github-issue-pr-workflow + child unavailable, timed out, failed, or invalid |
workflow/single_agent_fallback/no_child |
fallback |
authorized |
continue |
What ships with it
3 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.
- today Changed · +5 tokens per session f9a16817314d
- 1mo ago First seen · 107 lines · 96 tokens per session scan A 6ef6d12cef8e
execute-github-issue-pr-workflow is a skill published in the GitHub repository amazing-fish/agent-skills (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 101 tokens to every session and 3,055 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…