Skip to content
Agentmart
Submit a tool

diff

Compare a local routine .md file against its cloud state field by field.

Skill by hamzafer

IndexedMIT★ 10
Write a review

Chalk Labs

Need help deploying diff?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hamzafer-diff

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Compare a local routine .md file against its cloud state field by field. Read-only, no API writes. Invoke when the user says "diff <file>", "what's changed in <file>", or wants to preview drift between local and cloud before deploying.

Use cases: backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/diff

What's inside

Skill name
diff
Description
Compare a local routine .md file against its cloud state field by field. Read-only, no API writes. Invoke when the user says "diff <file>", "what's changed in <file>", or wants to preview drift between local and cloud before deploying.
License
MIT
Instructions
67 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# claude-routines:diff

Compare local vs cloud. Useful before `deploy` to see exactly what would change.

## Procedure

1. Parse the file's frontmatter and body. Expand `{{include}}` directives in the body (same as deploy does).
2. Read the file's `trigger_id`. If absent, abort with: `"no trigger_id in frontmatter; use create first"`.
3. Call `RemoteTrigger` with `action: "get"` and `trigger_id: <id>`.
4. Compare each tracked field. Skip read-only fields entirely.

## Tracked fields (compare and report differences)

- `name` (string equality)
- `cron_expression` or `run_once_at` (string equality on whichever is populated)
- `enabled` (bool equality)
- `job_config.ccr.environment_id` (string equality)
- `job_config.ccr.session_context.model` (string equality; treat absent on either side as equal)
- `job_config.ccr.session_context.allowed_tools` (set comparison; report added/removed individually)
- `job_config.ccr.session_context.sources` (list of objects; compare by `url`)
- `mcp_connections` (list of objects; compare by `connector_uuid`)
- Prompt body (compare file's expanded body against `job_config.ccr.events[0].data.message.content`)

## Read-only fields to skip

`created_at`, `updated_at`, `next_run_at`, `creator`, `ended_reason`, `api_token_hint`, `persist_session`, `enabled_plugins`, `extra_marketplaces`, `outcomes`, `last_fired_at`.

## Output format

```
trig_01ABC...  Norway News Digest

  cron:           "0 7 * * *"  ->  "0 8 * * *"
  allowed_tools:  +Bash  -KillBash
  prompt:         3 lines changed (+42 chars)

  ---  Send a Norway news digest with ONLY NEW stories...
  +++  Send a Norway news digest from the last 24 hours...

3 fields differ.
```

If everything matches:

```
trig_01ABC...  Norway News Digest
in sync.
```

## Whitespace handling

Trailing whitespace and trailing newlines are sometimes added or stripped by Anthropic's normalization. Report these as a special note: `prompt: trailing whitespace differs (semantically identical)`. Don't show this as a hard difference.

## Note on the model field

The API GET response does NOT echo the `model` field even when it's set. If your local file has `model: claude-opus-4-7` but the cloud response shows no model, treat this as `unknown - cannot verify`. Don't report it as a diff. (Verified 2026-05-14.)

## Bulk diff

For `diff all`, see the `bulk` skill.

## See also

- `dry-run deploy <file>` to see the exact body that would be sent on deploy
- `deploy <file>` to apply the changes after reviewing the diff

From hamzafer/claude-routines, MIT.

More from hamzafer/claude-routines

Signals

Stars
10
Forks
0
Open issues
0
Last commit (this folder)
May 14, 2026 (5 months ago)
Last release
Apr 27, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from hamzafer

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get diff running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying diff?

CallGet help
Cite this page

diff skill. Agent Mart. https://agentmart.dev/skills/hamzafer-diff (last updated 2026-10-24)