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 cisco-open/ai-harness-toolkit --skill pr-follow-upgit clone --depth 1 https://github.com/cisco-open/ai-harness-toolkitWrote 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/cisco-open/ai-harness-toolkit/pr-follow-up)<a href="https://agentmods.dev/skills/cisco-open/ai-harness-toolkit/pr-follow-up"><img src="https://agentmods.dev/badge/skills/cisco-open/ai-harness-toolkit/pr-follow-up/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/cisco-open/ai-harness-toolkit/pr-follow-up"><img src="https://agentmods.dev/badge/skills/cisco-open/ai-harness-toolkit/pr-follow-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01272 |
| Opus 5 | $0.00026 | $0.00636 |
| Sonnet 5 | $0.00010 | $0.00254 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
pr-follow-up 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 12d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Follow-up
Use this skill after a PR already exists. It is intentionally narrower than full CI self-healing: it watches for review comments, helps resolve them, and reports CI outcome. It does not require extra MCP servers.
When To Use
- The user says things like:
- "watch the PR"
- "handle PR comments as they come in"
- "monitor this PR and tell me if CI fails"
- "wait for comments, fix them, then keep watching"
- A PR has already been created, or can be discovered from the current branch.
Inputs
Accept any of:
- PR number
- PR URL
- current branch with an existing PR
If the PR is ambiguous, determine it with:
gh pr view --json number,url,title,headRefName,baseRefName
Scope
This skill should:
- Identify the PR for the current branch.
- Poll for new PR review comments.
- When comments appear, fetch the review threads and comment bodies.
- Present the new comments and ask the user whether to apply fixes.
- After fixes are validated, ask the user whether to resolve the addressed review threads.
- Use the
gh-pr-comment-resolutionworkflow to resolve review threads after approval. - Poll PR checks and notify on success or failure.
This skill should not:
- invent a full CI self-healing flow from scratch
- use unsupported interactive watch commands
- force-push or skip hooks without user approval
Default Workflow
1. Identify the PR
Prefer the PR for the current branch:
gh pr view --json number,url,title,headRefName,baseRefName,statusCheckRollup
If that fails, ask the user which PR to monitor.
2. Establish a baseline snapshot
Capture these once at the start:
gh pr view <PR_NUMBER> --json reviewThreads,statusCheckRollup,url,title
gh pr checks <PR_NUMBER>
Track:
- unresolved review thread ids
- current failing checks
3. Poll for updates
Use a short repeated loop with one-time status calls, not --watch flags.
Recommended calls:
gh pr view <PR_NUMBER> --json reviewThreads,statusCheckRollup,url,title
gh pr checks <PR_NUMBER>
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.
- 12d ago First seen · 198 lines · 51 tokens per session scan A 0f296f599ef4
pr-follow-up is a skill published in the GitHub repository cisco-open/ai-harness-toolkit (11 stars, last pushed 16d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,272 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
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.
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…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.