prompt-contract
Fill the nine-slot prompt contract, then grill, then hand off to a clean Claude session.
Skill by sardul3
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/sardul3-prompt-contract
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.
About
Use cases: documents, agent-building
Reviews
Write a reviewNo 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/prompt-contract
What's inside
- Skill name
prompt-contract- Description
- Fill the nine-slot prompt contract, then grill, then hand off to a clean Claude session. Use for new substantial tasks. Do not implement in this session.
- License
- MIT
- Instructions
- 47 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- reference.md
SKILL.md (first lines)
# Prompt contract You are in the **enrichment** session. Do **not** implement the user's task here. Do not open extra Cursor tabs. The work happens in a new `claude` CLI terminal after launch. If the user typed `/deep-ask ...`, treat the rest of the message as the original request. ## 1. Fill these nine slots Infer when obvious. Ask only for missing **high-impact** slots. Multiselect is allowed for role, audience, and length/tone. Do not ask for a raw model id unless they volunteer an override (`opus`, `sonnet`, `ultra`, or a profile name). | # | Slot | Notes | | - | ---- | ----- | | 1 | Role | senior backend, staff SRE, tech lead, security reviewer, … | | 2 | Audience | implementing agent, PR reviewer, beginner, future-you | | 3 | Goal | one-sentence deep ask **and** the deliverable | | 4 | Context | repo, stack, files, constraints; or “none / infer from repo” | | 5 | Constraints / non-goals | must / must not | | 6 | Output format | code+tests, plan only, diff, ADR, commands | | 7 | Length / tone | short, informal, rigorous, production-ready | | 8 | Success criteria | observable done-when | | 9 | Model profile | `fast` `code` `reason` `heavy` `vision` (auto; user may override) | Profile tie-break: vision if screenshots/UI; else heavy if many files / production / security; else reason if debug/design/investigate; else code if the output is code/tests; else fast. Optional (only if they change the work): examples, tools/sources, plan-then-code vs jump-to-code. See `reference.md` in this skill for the assembled markdown shape. ## 2. Grill Follow `~/.claude/skills/design-tree-interview/SKILL.md` (or `/grill-plan`). Fill remaining contract slots from the tree. Escape: “just go”, “skip grill”, `/skip-enrich`. If they get lost, `restate-plain`. ## 3. Handoff and launch When the frontier is empty (or they skip): 1. Follow `~/.claude/skills/session-handoff/SKILL.md`. Start the file with `<!-- PROMPT_CONTRACT_V1 -->` and include the nine slots plus original request. 2. Run (replace the path with the file you wrote): ```bash ~/.claude/hooks/prompt-enrich/launch-clean-claude.sh --file <handoff-path> ``` 3. Tell the user the saved path and that **work continues in the new terminal**. Suggest that session load `implement-terse`. 4. Stop. Do not start coding in this session. The new tab is the only implementer; this tab continuing will 429 OpenRouter.
From sardul3/dev-conductor, MIT.
More from sardul3/dev-conductor
- 0.524score
session-handoff
sardul3
Compact this conversation into a handoff file for a fresh agent.
SkillBFreshness: BClaude Code +9 - 0.524score
code-review
sardul3
Use after a feature, before merge or PR, or when the user asks for a review.
SkillBFreshness: BClaude Code +9 - 0.524score
design-tree-interview
sardul3
Relentless design-tree interview.
SkillBFreshness: BClaude Code +9 - 0.524score
dev-loop
sardul3
Start the Jira-to-PR developer loop for a ticket.
SkillBFreshness: BClaude Code +9 - 0.524score
domain-glossary
sardul3
Maintain CONTEXT.md glossary and sparse ADRs.
SkillBFreshness: BClaude Code +9 - 0.524score
agent-memory
sardul3
Persist durable agent metadata after self-review, user review, PR comments, or a correction.
SkillBFreshness: BClaude Code +9 - 0.523score
systematic-debugging
sardul3
Use when hitting a bug, test failure, or unexpected behavior, before proposing a fix.
SkillBFreshness: BClaude Code +9 - 0.521score
dev-loop-review
sardul3
Staff review for /dev-loop.
SkillBFreshness: BClaude Code +9 - 0.521score
lavish-ui
sardul3
Use Lavish (npx -y lavish-axi) when config lavish.enabled is on for this repo (default auto = UI repos only) and the Jira story is visual.
SkillBFreshness: BClaude Code +9 - 0.519score
jira-progress
sardul3
Move a Jira issue across configured workflow columns and comment as /dev-loop progresses.
SkillBFreshness: BClaude Code +9 - 0.519score
pr-comment-fixer
sardul3
Fix GitHub PR review comments for a watched /dev-loop PR.
SkillBFreshness: BClaude Code +9 - 0.519score
repo-memory
sardul3
Load or rebuild the hashed repo index for /dev-loop.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 30, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sardul3/dev-conductor
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sardul3
- 0.524score
code-review
sardul3
Use after a feature, before merge or PR, or when the user asks for a review.
SkillBFreshness: BClaude Code +9 - 0.524score
agent-memory
sardul3
Persist durable agent metadata after self-review, user review, PR comments, or a correction.
SkillBFreshness: BClaude Code +9 - 0.524score
dev-loop
sardul3
Start the Jira-to-PR developer loop for a ticket.
SkillBFreshness: BClaude Code +9 - 0.524score
domain-glossary
sardul3
Maintain CONTEXT.md glossary and sparse ADRs.
SkillBFreshness: BClaude Code +9 - 0.524score
design-tree-interview
sardul3
Relentless design-tree interview.
SkillBFreshness: BClaude Code +9 - 0.524score
session-handoff
sardul3
Compact this conversation into a handoff file for a fresh agent.
SkillBFreshness: BClaude Code +9
Cite this page
prompt-contract skill. Agent Mart. https://agentmart.dev/skills/sardul3-prompt-contract (last updated 2026-10-24)