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 commands/openshift-eng/ai-helpers/fix-cherrypick-robot-prgit clone --depth 1 https://github.com/openshift-eng/ai-helpersWrote 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/commands/openshift-eng/ai-helpers/fix-cherrypick-robot-pr)<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/fix-cherrypick-robot-pr"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/fix-cherrypick-robot-pr.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 5.1 | $0.00013 | $0.02103 |
| Opus 5 | $0.00006 | $0.01052 |
| Sonnet 5 | $0.00003 | $0.00421 |
| Haiku 4.5 | $0.00001 | $0.00210 |
Grade A, and why
fix-cherrypick-robot-pr 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- fix-cherrypick-robot-pr — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
git:fix-cherrypick-robot-pr
Synopsis
/git:fix-cherrypick-robot-pr <pr-url> [error-messages]
Description
The git:fix-cherrypick-robot-pr command replaces a cherrypick-robot PR with a clean, manually-crafted cherry-pick PR that includes fixes the robot cannot handle.
The cherrypick-robot creates automated PRs but cannot:
- Fix verification failures (JSON validation, missing annotations)
- Resolve merge conflicts
- Add context-specific fixes
- Handle edge cases requiring human judgment
- Apply repository-specific cleanup
This command helps you create a replacement PR with all necessary fixes applied.
Implementation
1. Extract Information from the Robot PR
Use gh pr view <pr-url> to extract:
- Base branch (e.g.,
release-4.19) - PR title (to extract bug ID like
OCPBUGS-65944) - All commit hashes included in the PR
- PR number for later closure
- Current PR checks/CI status
Example:
gh pr view <pr-url> --json baseRefName,title,commits,number,statusCheckRollup
2. Analyze Error Messages
Parse the provided error output to identify:
- Root causes (JSON validation, missing annotations, conflicts, etc.)
- Affected files
- Required fixes
- Fix strategy
Error sources (in priority order):
- User-provided error messages (from command arguments)
- File path if provided (e.g.,
/path/to/ci-errors.log) - CI failure URL if provided
- Automatically fetch from PR status checks
3. Discover Git Remotes and Create Branch
# Discover the upstream remote (the main repository)
# Look for a remote that's not owned by the current user
UPSTREAM_REMOTE=$(git remote -v | grep "fetch" | grep -v "$(git config user.name)" | awk '{print $1}' | head -1)
# Discover the fork remote (your fork)
FORK_REMOTE=$(git remote -v | grep "$(git config user.name).*push" | awk '{print $1}' | head -1)
# If not found, fall back to common names
UPSTREAM_REMOTE=${UPSTREAM_REMOTE:-upstream}
FORK_REMOTE=${FORK_REMOTE:-origin}
# Fetch the latest base branch
git fetch $UPSTREAM_REMOTE <base-branch>
# Create new branch following naming convention
git checkout -b cherry-pick-<issue-number>-to-<base-branch> $UPSTREAM_REMOTE/<base-branch>
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 First seen · 266 lines · 13 tokens per session scan A 8bd10358b080
fix-cherrypick-robot-pr is a command published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 2,103 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.