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 dimagi/commcare-android --skill docs-affected-by-branchgit clone --depth 1 https://github.com/dimagi/commcare-androidWrote 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/dimagi/commcare-android/docs-affected-by-branch)<a href="https://agentmods.dev/skills/dimagi/commcare-android/docs-affected-by-branch"><img src="https://agentmods.dev/badge/skills/dimagi/commcare-android/docs-affected-by-branch/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/dimagi/commcare-android/docs-affected-by-branch"><img src="https://agentmods.dev/badge/skills/dimagi/commcare-android/docs-affected-by-branch.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 | $0.00052 | $0.01056 |
| Opus 5.5 | $0.00021 | $0.00422 |
| Sonnet 5.5 | $0.00010 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
docs-affected-by-branch 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 5d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Affected by Branch
Find the Confluence pages the current branch makes out of date and list the edits each one needs. The code is the local checkout — don't clone anything.
Read confluence-docs.md first. Steps 4 and 5 use it.
Step 1: Check Atlassian access
Check whether the Atlassian MCP tools for Jira and Confluence are available. The later steps say what to do in each case.
If they are not available, tell the user before going further: you can't read Jira or Confluence, so you will ask them for the ticket's documentation links and for the pages that cover the change, and the report will list what changed for each page instead of exact edits.
Step 2: Get the ticket
Run gh pr view --json body,baseRefName to see whether the branch has a PR. Then take the
ticket from the first of these that applies:
- A ticket was passed as an argument — use it. "none" means there is no ticket.
- The branch has a PR whose description links a Jira ticket — use that ticket.
- Otherwise — ask the user for the Jira ticket key or URL. There may not be one, so accept "none".
If there is a ticket, collect the Confluence pages it links: its Documentation to Update list, or any Confluence links in its description. These are the pages the ticket expects to change.
- With Atlassian access: fetch the ticket and read the links from it.
- Without it: ask the user to paste the ticket's documentation links. Accept "none".
If the PR exists and its description has a Documentation section, collect the pages listed there too.
Step 3: Read the change
Diff the branch against its base, where <base> is the PR's baseRefName, or main when there
is no PR. Fetch first so the base is current:
git fetch origin <base>
git diff origin/<base>...HEAD
From the diff, collect the things a user can see or rely on: page and button labels, column headers, status names, error and notification strings, CSV column names, permissions, limits, and the names of new or changed features. Ignore refactors, tests and internal code that changes no behaviour.
What ships with it
1 file 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.
- 5d ago First seen · 102 lines · 52 tokens per session scan A dca6f65a527a
docs-affected-by-branch is a skill published in the GitHub repository dimagi/commcare-android (48 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 1,056 once invoked, about $0.0002 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 2026-11-15.
docs-affected-by-branch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docs-affected-by-branchdimagi/commcare-android | Skill | 48 | yesterday | Apache-2.0 | A | 52 | Claude Code |
| engineer-bot-getting-startedmakecindy/cindy | Skill | 10k | today | Apache-2.0 | A | 44 | Claude Code, Codex |
| engineer-bot-opsmakecindy/cindy | Skill | 10k | today | Apache-2.0 | A | 57 | Claude Code, Codex |
| shepherdchrisbanes/skills | Skill | 1.2k | yesterday | Apache-2.0 | A | 37 | Claude Code, Codex |
| release-kotlin-librarychrisbanes/skills | Skill | 1.2k | yesterday | Apache-2.0 | A | 46 | Claude Code |
| changelogchrisbanes/skills | Skill | 1.2k | yesterday | Apache-2.0 | A | 39 | Claude Code |
| release-new-versionniki914/zafiro | Skill | 381 | 2d ago | MIT | A | 48 | Claude Code, Codex |