plan
Plan mode for Kheish — inspect context, write a markdown plan into the active workspace's `.kheish/plans/` directory, and do not execute the work.
Skill by graniet
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/graniet-plan
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, writing
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 and code. 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/plan
What's inside
- Skill name
plan- Description
- Plan mode for Kheish — inspect context, write a markdown plan into the active workspace's `.kheish/plans/` directory, and do not execute the work.
- License
- MIT
- Instructions
- 60 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
## Kheish Compatibility
This skill is repo-local and stays inactive until explicitly activated.
When the original instructions refer to legacy tool names, use these Kheish mappings:
- `terminal` => `bash`
- `web_extract` => `web_fetch`, plus `web_search` when discovery is needed
- `search_files` => `grep_search` and `glob_search`
- `browser_*` tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitly
When the instructions mention local helper files, resolve them from `${KHEISH_SKILL_DIR}`.
# Plan Mode
Use this skill when the user wants a plan instead of execution.
## Core behavior
For this turn, you are planning only.
- Do not implement code.
- Do not edit project files except the plan markdown file.
- Do not run mutating terminal commands, commit, push, or perform external actions.
- You may inspect the repo or other context with read-only commands/tools when needed.
- Your deliverable is a markdown plan saved inside the active workspace under `.kheish/plans/`.
## Output requirements
Write a markdown plan that is concrete and actionable.
Include, when relevant:
- Goal
- Current context / assumptions
- Proposed approach
- Step-by-step plan
- Files likely to change
- Tests / validation
- Risks, tradeoffs, and open questions
If the task is code-related, include exact file paths, likely test targets, and verification steps.
## Save location
Save the plan with `write_file` under:
- `.kheish/plans/YYYY-MM-DD_HHMMSS-<slug>.md`
Treat that as relative to the active working directory / backend workspace. Kheish file tools are backend-aware, so using this relative path keeps the plan with the workspace on local, docker, ssh, modal, and daytona backends.
If the runtime provides a specific target path, use that exact path.
If not, create a sensible timestamped filename yourself under `.kheish/plans/`.
## Interaction style
- If the request is clear enough, write the plan directly.
- If no explicit instruction accompanies `/plan`, infer the task from the current conversation context.
- If it is genuinely underspecified, ask a brief clarifying question instead of guessing.
- After saving the plan, reply briefly with what you planned and the saved path.From graniet/kheish, MIT.
More from graniet/kheish
- 0.645score
peft
graniet
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
gguf
graniet
GGUF format and llama.cpp quantization for efficient CPU/GPU inference.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
vllm
graniet
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
creative-ideation
graniet
Generate project ideas through creative constraints.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
trl-fine-tuning
graniet
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
godmode
graniet
Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN…
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
modal
graniet
Serverless GPU cloud platform for running ML workloads.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
lm-evaluation-harness
graniet
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag).
SkillCFreshness: C★ 217Claude Code +9 - 0.641score
google-workspace
graniet
Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via gws CLI (googleworkspace/cli).
SkillCFreshness: C★ 217Claude Code +9 - 0.641score
find-nearby
graniet
Find nearby places (restaurants, cafes, bars, pharmacies, etc.) using OpenStreetMap.
SkillCFreshness: C★ 217Claude Code +9 - 0.639score
webhook-subscriptions
graniet
Create and manage webhook subscriptions for event-driven agent activation.
SkillCFreshness: C★ 217Claude Code +9 - 0.636score
xitter
graniet
Interact with X/Twitter via the x-cli terminal client using official X API credentials.
SkillCFreshness: C★ 217Claude Code +9
Signals
- Stars
- 217
- Forks
- 18
- Open issues
- 0
- Last commit (this folder)
- Jun 25, 2026 (4 months ago)
- Last release
- Jun 27, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/graniet/kheish
- Website
- kheish.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from graniet
- 0.645score
vllm
graniet
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
gguf
graniet
GGUF format and llama.cpp quantization for efficient CPU/GPU inference.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
creative-ideation
graniet
Generate project ideas through creative constraints.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
lm-evaluation-harness
graniet
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag).
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
modal
graniet
Serverless GPU cloud platform for running ML workloads.
SkillCFreshness: C★ 217Claude Code +9 - 0.645score
peft
graniet
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
SkillCFreshness: C★ 217Claude Code +9
Cite this page
plan skill. Agent Mart. https://agentmart.dev/skills/graniet-plan (last updated 2026-10-24)