Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Shape an engineering problem without assuming a solution or forcing a project phase.
Install H Frame
$ npx skills add m0n0x41d/haft --skill h-frame -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install m0n0x41d/haft h-frame --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/m0n0x41d/haft.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/cli/skill/h-frame .claude/skills/h-frame && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "h-frame" agent skill from https://github.com/m0n0x41d/haft/tree/main/internal/cli/skill/h-frame into .claude/skills/h-frame/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h-frame", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/m0n0x41d/haft/tree/main/internal/cli/skill/h-frameType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add m0n0x41d/haft --skill h-frame -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install m0n0x41d/haft h-frame --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/m0n0x41d/haft.git skills-src && mkdir -p .agents/skills && cp -r skills-src/internal/cli/skill/h-frame .agents/skills/h-frame && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "h-frame" agent skill from https://github.com/m0n0x41d/haft/tree/main/internal/cli/skill/h-frame into .agents/skills/h-frame/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h-frame", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add m0n0x41d/haft --skill h-frame -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install m0n0x41d/haft h-frame --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/m0n0x41d/haft.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/internal/cli/skill/h-frame .cursor/skills/h-frame && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "h-frame" agent skill from https://github.com/m0n0x41d/haft/tree/main/internal/cli/skill/h-frame into .cursor/skills/h-frame/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h-frame", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/m0n0x41d/haft.git --path internal/cli/skill/h-frame--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add m0n0x41d/haft --skill h-frame -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install m0n0x41d/haft h-frame --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/m0n0x41d/haft.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/internal/cli/skill/h-frame .gemini/skills/h-frame && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "h-frame" agent skill from https://github.com/m0n0x41d/haft/tree/main/internal/cli/skill/h-frame into .gemini/skills/h-frame/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h-frame", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install m0n0x41d/haft h-frameInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add m0n0x41d/haft --skill h-frame -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/m0n0x41d/haft.git skills-src && mkdir -p .github/skills && cp -r skills-src/internal/cli/skill/h-frame .github/skills/h-frame && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "h-frame" agent skill from https://github.com/m0n0x41d/haft/tree/main/internal/cli/skill/h-frame into .github/skills/h-frame/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h-frame", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add m0n0x41d/haft --skill h-frame -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install m0n0x41d/haft h-frame --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/m0n0x41d/haft.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/internal/cli/skill/h-frame .opencode/skills/h-frame && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "h-frame" agent skill from https://github.com/m0n0x41d/haft/tree/main/internal/cli/skill/h-frame into .opencode/skills/h-frame/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h-frame", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
h-frame- GitHub stars
- 1.4k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 641 words
- Files
- 1
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Shape an engineering problem without assuming a solution or forcing a project phase.
- Works in 6 steps: Stabilize the signal. Separate what was… → Restore overloaded words. Replace vague… → Classify only if useful. Diagnosis,… → …
- Proposal arrives before the affected object
- SKILL.md covers Conditional project-memory…, Procedure, When a ProblemCard is warranted and Persistent form, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
H Frame is an agent skill from m0n0x41d/haft. Shape an engineering problem without assuming a solution or forcing a project phase. Use when a redesign, refactor, or proposal arrives before the affected object, observed signal, constraints, unresolved relation, and acceptance basis are clear. Default to a conversational frame; record a ProblemCard only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs a durable accepted problem statement. Prefer h-diagnose for a concrete failure with…
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.
When your agent uses it
- Proposal arrives before the affected object
- Observed signal
- Unresolved relation
- Acceptance basis are clear
Example prompts
- “/h-frame”
Requirements
- Pre-approved tools (allowed-tools): Bash, Read, Grep, Glob, mcp__haft__haft_problem, mcp__haft__haft_query
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Stabilize the signal. Separate what was observed from assumed cause and
- Restore overloaded words. Replace vague terms such as quality,
- Classify only if useful. Diagnosis, optimization, search, or synthesis
- State scope and constraints. Say what is in and out. Separate hard
- Draft acceptance. Propose an observable solved condition and label it as
- Keep solution content out. If a proposed method exposed the problem,
What it can do on your machine
Read from SKILL.md and the folder at commit e0c63f4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadGrepGlobmcp__haft__haft_problemmcp__haft__haft_query
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
H Frame loads about 1.6k tokens when it runs. Until then it costs about 134 tokens; SKILL.md has 641 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, Grep, Glob, mcp__haft__haft_problem, mcp__haft__haft_query
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 641 words (~1,575 tokens).
“Use the FPF source for problem shaping rather than a hard-coded route. For an exact SourceID or UnitID, call mcphafthaft_query(action="fpf", mode="inspect", identifier="..."). Otherwise use mode="concern" with the operator's query, then inspect the direct pattern body before relying on it. A…”
- name
- h-frame
- allowed-tools
- Bash, Read, Grep, Glob, mcp__haft__haft_problem, mcp__haft__haft_query
- when_to_use
- The problem itself is current and under-articulated. This skill may be used independently; it does not require or imply later exploration, comparison, or…
- argument-hint
- [problem signal or proposed change]
Files
Just SKILL.md in internal/cli/skill/h-frame of m0n0x41d/haft.
Open the folder on GitHubat commit e0c63f4
Compare with similar skills
H Frame next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| H Frame this skillm0n0x41d/haft | 1.4k | — | ~1.6k | Automated safety check: Notes | Custom licence | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from m0n0x41d/haft
All 24 skills in this repoH Decide
m0n0x41d/haft
Routes one direct, unambiguous operator request to bind a bounded choice as a DecisionRecord.
H Explore
m0n0x41d/haft
Generate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each kept visible.
H Onboard
m0n0x41d/haft
Bootstrap Haft through one readable onboarding surface, prepare an initial profile review or one bounded existing-scope relation change, and orient applicable specification carriers.
H Spec
m0n0x41d/haft
Manage Haft's typed specification lifecycle and source-currentness repair: inspect current SpecSections, draft or clarify carriers, classify FPF semantic fanout, record operator-requested spec…
H Status
m0n0x41d/haft
Read-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module decision coverage, and bounded exact file-link gaps from a…
H Verify
m0n0x41d/haft
Verifies that a recorded DecisionRecord still holds — baseline-vs-measure evidence loop with drift detection per FPF Evidence Decay.
Related
Categories
Questions about H Frame
What does H Frame do?
Shape an engineering problem without assuming a solution or forcing a project phase. H Frame is an agent skill from m0n0x41d/haft. Shape an engineering problem without assuming a solution or forcing a project phase.
When should I use H Frame?
H Frame fits situations like: proposal arrives before the affected object; observed signal; unresolved relation; acceptance basis are clear.
How do I install H Frame in Claude Code?
Run `npx skills add m0n0x41d/haft --skill h-frame -a claude-code`. Or copy the skill folder (internal/cli/skill/h-frame in m0n0x41d/haft) into .claude/skills/h-frame in your project. Claude Code loads it when a task matches its description.
How do I install H Frame in Codex?
Run `npx skills add m0n0x41d/haft --skill h-frame -a codex`. Or copy the skill folder (internal/cli/skill/h-frame in m0n0x41d/haft) into .agents/skills/h-frame in your project. Codex loads it when a task matches its description.
Can I use H Frame in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add m0n0x41d/haft --skill h-frame -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/h-frame, .gemini/skills/h-frame, .github/skills/h-frame and .opencode/skills/h-frame in your project.
What does H Frame need to run?
SKILL.md names no scripts, command-line tools or credentials: H Frame is instructions for the agent only. Its frontmatter pre-approves these tools: Bash, Read, Grep, Glob, mcp__haft__haft_problem, mcp__haft__haft_query.
Does H Frame access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is H Frame safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does H Frame use?
H Frame has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does H Frame use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to H Frame?
Skills that share tags, products or a category with H Frame: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains H Frame?
m0n0x41d (a GitHub user) maintains it in m0n0x41d/haft, which has 1,397 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on September 28, 2026.
Source: m0n0x41d/haft on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.