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/redescribegit 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/redescribe)<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/redescribe"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/redescribe.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 | $0.00015 | $0.01126 |
| Opus 5 | $0.00008 | $0.00563 |
| Sonnet 5 | $0.00003 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
redescribe 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 yesterday.
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:
- redescribe — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
git:redescribe
Synopsis
/git:redescribe # Redescribe the PR for the current branch
/git:redescribe <pr-url> # Redescribe a specific PR by URL
Description
The /git:redescribe command analyzes a Pull Request's actual code changes (diffs) and commit messages to generate an accurate, up-to-date PR description. It compares the existing description with the reality of the code, proposes a corrected description, and offers to update the PR.
This is particularly useful when:
- A PR has evolved significantly since it was opened.
- The initial description was placeholder text.
- Commits have been squashed or rebased, changing the PR's scope.
The command ensures the description accurately reflects:
- The problem being solved (from commit messages/Jira context).
- The changes made (from code diffs).
- The implementation details.
Implementation
1. Identify Target PR
Determine which PR to operate on:
- If
<pr-url>is provided: Use that PR. - If no argument:
- Context Discovery: Run
git remote -vto identify the repository (preferupstream, thenorigin). - Run
gh pr view --repo <owner>/<repo> --json urlto find the PR associated with the current branch. This proactively avoids "No default remote" errors. - If no PR is found, error out and ask the user to provide a URL or push the branch/open a PR.
- Context Discovery: Run
2. Gather Context
Collect necessary information using the GitHub CLI (gh) and git:
-
Fetch PR Details:
gh pr view <pr-url> --json title,body,baseRefName,headRefName,numbertitle: For context (often contains Jira ID).body: The current description (to see what needs changing).headRefName: The source branch.
-
Fetch Commits:
gh pr view <pr-url> --json commits # OR if local: git log <base>..<head>- Extract commit messages to understand the intent and history.
-
Fetch Code Diffs:
gh pr diff <pr-url>- Analyze the actual code changes.
- Note: If the diff is very large, prioritize file names, structural changes, and distinct code blocks to avoid context window limits.
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.
- yesterday First seen · 128 lines · 15 tokens per session scan A 60f7cae2091a
redescribe is a command published in the GitHub repository openshift-eng/ai-helpers (114 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 1,126 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.