Skip to content
Agentmart
Submit a tool

bounds-mode

Coordinate a task with Bounds workflows when the user explicitly asks for bounds-mode.

Skill by boundsj

IndexedMIT
Write a review

Chalk Labs

Need help deploying bounds-mode?

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/boundsj-bounds-mode

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

Coordinate a task with Bounds workflows when the user explicitly asks for bounds-mode. Select only the skills needed for the current work.

Use cases: productivity

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/bounds-mode

What's inside

Skill name
bounds-mode
Description
Coordinate a task with Bounds workflows when the user explicitly asks for bounds-mode. Select only the skills needed for the current work.
License
MIT
Instructions
37 lines in SKILL.md · view on GitHub

Files (5)

  • LICENSE.txt
  • NOTICE.md
  • SKILL.md
  • openai.yaml · agents/
  • hosts.md · references/

SKILL.md (first lines)

# Bounds mode

Use this entrypoint only when explicitly requested. Optimize for accepted work per minute of human attention: preserve the task, resolve routine details from evidence, and keep small requests small. This skill adds no permissions or external actions.

## Route the task

Read the relevant project instructions and available skill descriptions. Load a supporting skill's body only when its phase is needed, through host discovery. Load references conditionally.

| Need | Skill |
| --- | --- |
| Material scope, behavior, or dependency decisions | `bounds-plan` |
| An observed failure or regression | `bounds-debug` |
| A requested review or consequential implementation to check | `bounds-review` |
| An authorized change to finish through PR readiness | `bounds-ship` |
| A stale or inherited PR to reassess and update | `bounds-modernize` |
| Authorized GitHub comments on the user’s behalf | `bounds-leaving-pr-comments` |
| Prior decisions or unfinished work to recover | `bounds-recall` |
| Repeated corrections or avoidable work to examine | `bounds-retro` |
| Agent documentation to create or repair | `bounds-agent-docs` |
| A reusable project verification recipe to establish | `bounds-create-verification` |
| An existing recipe or feature map to refresh | `bounds-maintain-verification` |
| Progress since the user's last message | `bounds-ketchup` |
| Rationale behind existing code | `bounds-why` |
| Downstream effects of a change | `bounds-blast-radius` |
| A code walkthrough or explanation | `bounds-how` |
| Interfaces and state ownership to design | `bounds-architect` |
| Requested prose to tighten | `bounds-unslop` |
| A reusable working-style skill | `bounds-automate-me` |

Keep phases proportional: inspect a typo directly; reproduce a bug first. A request for a plan or review ends with that deliverable; it does not authorize implementation. Preserve relevant specialist skills and native tools.

Carry authorized implementation through the agreed acceptance checks. Use the project's existing verification recipe when useful; creating one is a separate need, not a compulsory phase. Report the outcome, evidence, and consequential gaps. Use independent review when warranted, available, and permitted by existing user and host instructions, under `bounds-review`'s bounded protocol. Reuse authorization already granted.

If a selected skill is absent, say which one. Continue with the available tools when feasible, without pretending it loaded or installing dependencies unasked.

## Continuity

Honor opt-out immediately. Follow the user's continuing task while context retains it; there is no portable sticky-mode switch. Do not persist a mode setting or modify standing instructions. For invocation, fresh-session discovery, or host limitations, read [host behavior](references/hosts.md).

From boundsj/bounds-skills, MIT.

More from boundsj/bounds-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 17, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from boundsj

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 bounds-mode 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 bounds-mode?

CallGet help
Cite this page

bounds-mode skill. Agent Mart. https://agentmart.dev/skills/boundsj-bounds-mode (last updated 2026-10-24)