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/roocodeinc/roo-code/releasegit clone --depth 1 https://github.com/RooCodeInc/Roo-CodeWhat 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 | $0.00009 | $0.00892 |
| Opus 5 | $0.00005 | $0.00446 |
| Sonnet 5 | $0.00002 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
release 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.
What it actually says
- Identify the SHA corresponding to the most recent release using GitHub CLI:
gh release view --json tagName,targetCommitish,publishedAt - Analyze changes since the last release using:
gh pr list --state merged --base main --json number,title,author,url,mergedAt,closingIssuesReferences --limit 1000 -q '[.[] | select(.mergedAt > "TIMESTAMP") | {number, title, author: .author.login, url, mergedAt, issues: .closingIssuesReferences}] | sort_by(.number)' - For each PR with linked issues, fetch the issue details to get the issue reporter:
gh issue view ISSUE_NUMBER --json number,author -q '{number, reporter: .author.login}' - Summarize the changes. If the user did not specify, ask them whether this should be a major, minor, or patch release.
- Create a changeset in .changeset/v[version].md instead of directly modifying package.json. The format is:
---
"roo-cline": patch|minor|major
---
[list of changes]
- Always include contributor attribution and the PR number: use "(PR # by @username)".
- For PRs that close issues, include both the issue number and the PR number and authors: "- Fix: Description (#123 by @reporter, PR #456 by @contributor)"
- For PRs without linked issues, include the PR number and author: "- Add support for feature (PR #456 by @contributor)"
- Provide brief descriptions of each item to explain the change
- Order the list from most important to least important
- Example formats:
- With issue: "- Fix: Resolve memory leak in extension (#456 by @issueReporter, PR #789 by @prAuthor)"
- Without issue: "- Add support for Gemini 2.5 Pro caching (PR #789 by @contributor)"
- CRITICAL: Include EVERY SINGLE PR in the changeset - don't assume you know which ones are important. Count the total PRs to verify completeness and cross-reference the list to ensure nothing is missed.
- If the generate_image tool is available, create a release image at
releases/[version]-release.png- The image should feature a realistic-looking kangaroo doing something human-like that relates to the main highlight of the release
- Pass
releases/template.pngas the reference image for aspect ratio and kangaroo style - Add the generated image to .changeset/v[version].md before the list of changes with format:

- If a major or minor release:
- Ask the user what the three most important areas to highlight are in the release
- Update the English version relevant announcement files and documentation (webview-ui/src/components/chat/Announcement.tsx, README.md, and the
latestAnnouncementIdin src/core/webview/ClineProvider.ts) - Ask the user to confirm that the English version looks good to them before proceeding
- Use the new_task tool to create a subtask in
translatemode with detailed instructions of which content needs to be translated into all supported languages (The READMEs as well as the translation strings)
- Create a new branch for the release preparation:
git checkout -b release/v[version] - Commit and push the changeset file and any documentation updates to the repository:
git add . && git commit -m "chore: add changeset for v[version]" && git push origin release/v[version] - Create a pull request for the release:
gh pr create --title "Release v[version]" --body "Release preparation for v[version]. This PR includes the changeset and any necessary documentation updates." --base main --head release/v[version] - The GitHub Actions workflow will automatically:
- Create a version bump PR when changesets are merged to main
- Update the CHANGELOG.md with proper formatting
- Publish the release when the version bump PR is merged
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 · 46 lines · 9 tokens per session scan A 9f8168004925
release is a command published in the GitHub repository RooCodeInc/Roo-Code (24,320 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 892 once invoked, about $0.0000 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 2026-08-30.
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.
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.