Agent skill

Tbd

by jlevy in jlevy/strif

Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents.

MITAuto-check passedDevelopment

Install Tbd

skills CLI
$ npx skills add jlevy/strif --skill tbd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jlevy/strif tbd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jlevy/strif.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/tbd .claude/skills/tbd && rm -rf skills-src

Use ~/.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/

Facts

Skill name
tbd
GitHub stars
131
Token cost
~3.5k tokens
SKILL.md length
1,349 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents.

  • Works in 4 steps: Beads: Git-native issue tracking (tasks,… → Spec-Driven Workflows: Plan features →… → Knowledge Injection: 17+ engineering… → …
  • : tracking issues/beads with dependencies
  • SKILL.md covers Installation, Routine Commands, CRITICAL: You Operate tbd —… and User Request → Agent Action, plus 6 more sections
  • Calls npm

What it does

Tbd is an agent skill from jlevy/strif. Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Drop-in replacement for bd/Beads with simpler architecture. Use for: tracking issues/beads with dependencies, creating bugs/features/tasks, planning specs, implementing features from specs, code reviews, committing code, creating PRs, loading coding guidelines (TypeScript, Python, TDD, golden testing, Convex, monorepo patterns), code cleanup, research briefs, architecture docs, agent handoffs, and…

Its SKILL.md is about 3.5k 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, covering Test-driven development, Code review and Task management. It works with Python, TypeScript and Git. The repository describes itself as: A tiny, useful Python lib of string, file, and object utilities. The licence is MIT.

When your agent uses it

  • : tracking issues/beads with dependencies
  • Creating bugs/features/tasks
  • Implementing features from specs
  • Committing code

Example prompts

  • “/tbd”

Requirements

  • Python 3
  • Node.js
  • Pre-approved tools (allowed-tools): Bash(tbd:*), Read, Write

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Beads: Git-native issue tracking (tasks, bugs, features).
  2. Spec-Driven Workflows: Plan features → break into beads → implement
  3. Knowledge Injection: 17+ engineering guidelines (TypeScript, Python, TDD,
  4. Shortcuts: Reusable instruction templates for common workflows (code review,

What it can do on your machine

Read from SKILL.md and the folder at commit f66ba7e. 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:

    • Bash(tbd:*)
    • Read
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    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

Tbd loads about 3.5k tokens when it runs. Until then it costs about 256 tokens; SKILL.md has 1,349 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~256
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k

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 passed

The automated check found no risky patterns in SKILL.md.

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

The full file from jlevy/strif at commit f66ba7e, republished under its MIT licence (© jlevy). 1,349 words, ~3,470 tokens.

Download SKILL.mdSave it as .claude/skills/tbd/SKILL.md (or your agent's skills folder).
name
tbd
description
Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Drop-in replacement for bd/Beads with simpler architecture. Use for: tracking issues/beads with dependencies, creating bugs/features/tasks, planning specs, implementing features from specs, code reviews, committing code, creating PRs, loading coding guidelines (TypeScript, Python, TDD, golden testing, Convex, monorepo patterns), code cleanup, research briefs, architecture docs, agent handoffs, and checking out third-party library source code. Invoke when user mentions: tbd, beads, bd, shortcuts, issues, bugs, tasks, features, epics, todo, tracking, specs, planning, implementation, validation, guidelines, templates, commit, PR, pull request, code review, testing, TDD, test-driven, golden testing, snapshot testing, TypeScript, Python, Convex, monorepo, cleanup, dead code, refactor, handoff, research, architecture, labels, search, checkout library, source code review, or any workflow shortcut.
allowed-tools
Bash(tbd:*), Read, Write
<!-- DO NOT EDIT: Generated by tbd setup.
Run 'tbd setup' to update.
-->

title: tbd Workflow description: Full tbd workflow guide for agents

tbd helps humans and agents ship code with greater speed, quality, and discipline.

  1. Beads: Git-native issue tracking (tasks, bugs, features). Never lose work across sessions. Drop-in replacement for bd.
  2. Spec-Driven Workflows: Plan features → break into beads → implement systematically.
  3. Knowledge Injection: 17+ engineering guidelines (TypeScript, Python, TDD, testing, Convex, monorepos) available on demand.
  4. Shortcuts: Reusable instruction templates for common workflows (code review, commits, PRs, cleanup, handoffs).

Installation

bash
npm install -g get-tbd@latest
tbd setup --auto --prefix=<name>   # Fresh project (--prefix is REQUIRED: 2-8 alphabetic chars recommended. ALWAYS ASK THE USER FOR THE PREFIX; do not guess it)
tbd setup --auto                   # Existing tbd project (prefix already set)
tbd setup --from-beads             # Migration from .beads/ if `bd` has been used

Routine Commands

bash
tbd --help    # Command reference
tbd status    # Status
tbd doctor    # If there are problems

tbd setup --auto   # Run any time to refresh setup
tbd prime      # Restore full context on tbd after compaction

CRITICAL: You Operate tbd — The User Doesn’t

You are the tbd operator: Users talk naturally; you translate their requests to tbd actions. DO NOT tell users to run tbd commands. That’s your job.

  • WRONG: “Run tbd create to track this bug”

  • RIGHT: (you run tbd create yourself and tell the user it’s tracked)

Welcoming a user: When users ask “what is tbd?” or want help → run tbd shortcut welcome-user

User Request → Agent Action

User SaysYou (the Agent) Run
Issues/Beads
“There’s a bug where …”tbd create "..." --type=bug
“Create a task/feature for …”tbd create "..." --type=task or --type=feature
“Let’s work on issues/beads”tbd ready
“Show me issue X”tbd show <id>
“Close this issue”tbd close <id>
“Search issues for X”tbd search "X"
“Add label X to issue”tbd label add <id> <label>
“What issues are stale?”tbd stale
Planning & Specs
“Plan a new feature” / “Create a spec”tbd shortcut new-plan-spec
“Break spec into beads”tbd shortcut plan-implementation-with-beads
“Implement these beads”tbd shortcut implement-beads
Code Review & Commits
“Review this code” / “Code review”tbd shortcut review-code
“Review this PR”tbd shortcut review-github-pr
“Commit this” / “Use the commit shortcut”tbd shortcut code-review-and-commit
“Create a PR” / “File a PR”tbd shortcut create-or-update-pr-simple
“Merge main into my branch”tbd shortcut merge-upstream
Guidelines & Knowledge
“Use TypeScript best practices”tbd guidelines typescript-rules
“Use Python best practices”tbd guidelines python-rules
“Build a TypeScript CLI”tbd guidelines typescript-cli-tool-rules
“Improve monorepo setup”tbd guidelines pnpm-monorepo-patterns or bun-monorepo-patterns
“Add golden/e2e testing”tbd guidelines golden-testing-guidelines
“Use TDD” / “Test-driven development”tbd guidelines general-tdd-guidelines
“Convex best practices”tbd guidelines convex-rules
Documentation
“Research this topic”tbd shortcut new-research-brief
“Document architecture”tbd shortcut new-architecture-doc
Cleanup & Maintenance
“Clean up this code” / “Remove dead code”tbd shortcut code-cleanup-all
“Fix repository problems”tbd doctor --fix
Sessions & Handoffs
“Hand off to another agent”tbd shortcut agent-handoff
“Check out this library’s source”tbd shortcut checkout-third-party-repo
(your choice whenever appropriate)tbd list, tbd dep add, tbd close, tbd sync, etc.

Note: Never gitignore .tbd/workspaces/ — the outbox must be committed to your working branch. See tbd guidelines tbd-sync-troubleshooting for details.

CRITICAL: Session Closing Protocol

Before saying “done”, you MUST complete this checklist:

[ ] 1. git add + git commit
[ ] 2. git push
[ ] 3. gh pr checks <PR> --watch 2>&1 (IMPORTANT: WAIT for final summary, do NOT tell user it is done until you confirm it passes CI!)
[ ] 4. tbd close/update <id> for all beads worked on
[ ] 5. tbd sync
[ ] 6. CONFIRM CI passed (if failed: fix, run tests, re-push, restart from step 3)

Work is not done until pushed, CI passes, and tbd is synced.

Bead Tracking Rules

  • Track all task work not done immediately as beads (discovered work, TODOs, multi-session work)
  • When in doubt, create a bead
  • Check tbd ready when not given specific directions
  • Always close/update beads and run tbd sync at session end

Commands

Finding Work
CommandPurpose
tbd readyBeads ready to work (no blockers)
tbd list --status openAll open beads
tbd list --status in_progressYour active work
tbd show <id>Bead details with dependencies
Creating & Updating
CommandPurpose
tbd create "title" --type task|bug|feature --priority=P2New bead (P0-P4, not “high/medium/low”)
tbd update <id> --status in_progressClaim work
tbd close <id> [--reason "..."]Mark complete
Dependencies & Sync
CommandPurpose
tbd dep add <bead> <depends-on>Add dependency
tbd blockedShow blocked beads
tbd syncSync with git remote (run at session end)
tbd statsProject statistics
tbd doctorCheck for problems
tbd doctor --fixAuto-fix repository problems
CommandPurpose
tbd search <query>Search issues by text
tbd label add <id> <label>Add label to issue
tbd label remove <id> <label>Remove label from issue
tbd label listList all labels in use
tbd staleList issues not updated recently
Documentation
CommandPurpose
tbd shortcut <name>Run a shortcut
tbd shortcut --listList shortcuts
tbd guidelines <name>Load coding guidelines
tbd guidelines --listList guidelines
tbd template <name>Output a template

Quick Reference

  • Priority: P0=critical, P1=high, P2=medium (default), P3=low, P4=backlog
  • Types: task, bug, feature, epic
  • Status: open, in_progress, closed
  • JSON output: Add --json to any command
<!-- BEGIN SHORTCUT DIRECTORY -->
Show full SKILL.md (665 more words)Show less

Available Shortcuts

Run tbd shortcut <name> to use any of these shortcuts:

NameDescription
agent-handoffGenerate a concise handoff prompt for another coding agent to continue work
checkout-third-party-repoGet source code for libraries and third-party repos using git. Essential for reliable source code review. Prefer this to web searches or fetching of web pages from github.com as it is far more effective (github.com blocks web scraping from main website).
code-cleanup-allFull cleanup cycle including duplicate removal, dead code, and code quality improvements
code-cleanup-docstringsReview and add concise docstrings to major functions and types
code-cleanup-testsReview and remove tests that do not add meaningful coverage
code-review-and-commitRun pre-commit checks, review changes, and commit code
coding-spikePrototype to validate a spec through hands-on implementation
create-or-update-pr-simpleCreate or update a pull request with a concise summary
create-or-update-pr-with-validation-planCreate or update a pull request with a detailed test/validation plan
implement-beadsImplement beads from a spec, following TDD and project rules
merge-upstreamMerge origin/main into current branch with conflict resolution
new-architecture-docCreate an architecture document for a system or component design
new-guidelineCreate a new coding guideline document for tbd
new-plan-specCreate a new feature planning specification document
new-qa-playbookCreate a QA test playbook for manual validation workflows
new-research-briefCreate a research document for investigating a topic or technology
new-shortcutCreate a new shortcut (reusable instruction template) for tbd
new-validation-planCreate a validation/test plan showing what's tested and what remains
plan-implementation-with-beadsCreate implementation beads from a feature planning spec
precommit-processFull pre-commit checklist including spec sync, code review, and testing
review-codeComprehensive code review for uncommitted changes, branch work, or GitHub PRs
review-code-pythonPython-focused code review (language-specific rules only)
review-code-typescriptTypeScript-focused code review (language-specific rules only)
review-github-prReview a GitHub pull request with follow-up actions (comment, fix, CI check)
revise-all-architecture-docsComprehensive revision of all current architecture documents
revise-architecture-docUpdate an architecture document to reflect current codebase state
setup-github-cliEnsure GitHub CLI (gh) is installed and working
sync-failure-recoveryHandle tbd sync failures by saving to workspace and recovering later
update-specs-statusReview active specs and sync their status with tbd issues
welcome-userWelcome message for users after tbd installation or setup

Available Guidelines

Run tbd guidelines <name> to apply any of these guidelines:

NameDescription
backward-compatibility-rulesGuidelines for maintaining backward compatibility across code, APIs, file formats, and database schemas
bun-monorepo-patternsModern patterns for Bun-based TypeScript monorepo architecture
cli-agent-skill-patternsBest practices for building TypeScript CLIs that function as agent skills in Claude Code and other AI coding agents
commit-conventionsConventional Commits format with extensions for agentic workflows
convex-limits-best-practicesComprehensive reference for Convex platform limits, workarounds, and performance best practices
convex-rulesGuidelines and best practices for building Convex projects, including database schema design, queries, mutations, and real-world examples
electron-app-development-patternsGuidelines for Electron development ecosystems including npm, pnpm, and Bun, with security baselines and framework comparisons
error-handling-rulesRules for handling errors, failures, and exceptional conditions
general-coding-rulesRules for constants, magic numbers, and general coding practices
general-comment-rulesLanguage-agnostic rules for writing clean, maintainable comments
general-eng-assistant-rulesRules for AI assistants acting as senior engineers, including objectivity and communication guidelines
general-style-rulesStyle guidelines for auto-formatting, emoji usage, and output formatting
general-tdd-guidelinesTest-Driven Development methodology and best practices
general-testing-rulesRules for writing minimal, effective tests with maximum coverage
golden-testing-guidelinesGuidelines for implementing golden/snapshot testing for complex systems
pnpm-monorepo-patternsModern patterns for pnpm-based TypeScript monorepo architecture
python-cli-patternsModern patterns for Python CLI application architecture
python-modern-guidelinesGuidelines for modern Python projects using uv, with a few more opinionated practices
python-rulesGeneral Python coding rules and best practices
release-notes-guidelinesGuidelines for writing clear, accurate release notes
tbd-sync-troubleshootingCommon issues and solutions for tbd sync and workspace operations
typescript-cli-tool-rulesRules for building CLI tools with Commander.js, picocolors, and TypeScript
typescript-code-coverageBest practices for code coverage in TypeScript with Vitest and v8 provider
typescript-rulesTypeScript coding rules and best practices
typescript-sorting-patternsDeterministic sorting patterns and comparison chains for TypeScript
typescript-yaml-handling-rulesBest practices for parsing and serializing YAML in TypeScript
writing-style-guidelinesGuidelines for clear, concise, and reader-friendly writing in documentation and code
<!-- END SHORTCUT DIRECTORY -->

© jlevy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/tbd of jlevy/strif.

Open the folder on GitHubat commit f66ba7e

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in jlevy/strif, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Tbd 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.

Tbd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tbd this skilljlevy/strif131—~3.5kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Subagent-Driven DevelopmentHoangNguyen0403/agent-skills-standard571—~1.3kAutomated safety check: PassMIT
Skyvern Version BumpSkyvern-AI/skyvern23k—~1kAutomated safety check: NotesAGPL-3.0
Git History Bug Auditben-manes/caffeine18k—~3.3kAutomated safety check: PassApache-2.0
Code Reviewerjewbetcha/opentrace1162 repos~1.1kAutomated safety check: NotesMIT

Similar skills

  • 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.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Subagent-Driven Development

    HoangNguyen0403/agent-skills-standard

    Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.

    571 GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Skyvern Version Bump

    Skyvern-AI/skyvern

    Walks through a Skyvern open-source release bump: update the version, rebuild the Python and TypeScript SDKs with Fern, commit, and open a pull request.

    23k GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check: notes
  • Git History Bug Audit

    ben-manes/caffeine

    Audits a module by walking its git history commit by commit, tracking unresolved issues forward, and reporting the ones that survive to HEAD as findings.

    18k GitHub stars~3.3k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Code Reviewer

    jewbetcha/opentrace

    Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go.

    116 GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check: notes
  • Qt6 QML Code Reviewer

    x-tools-author/x-tools

    Runs a 47-rule deterministic QML linter, then six parallel deep-analysis passes over bindings, layout, loaders, delegates, states, and performance.

    1.1k GitHub starsUsed in 1 repo~3.6k tokens
    DevelopmentAuto-check passed

Categories

Questions about Tbd

What does Tbd do?

Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Tbd is an agent skill from jlevy/strif. Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents.

When should I use Tbd?

Tbd fits situations like: : tracking issues/beads with dependencies; creating bugs/features/tasks; implementing features from specs; committing code.

How do I install Tbd in Claude Code?

Run `npx skills add jlevy/strif --skill tbd -a claude-code`. Or copy the skill folder (.claude/skills/tbd in jlevy/strif) into .claude/skills/tbd in your project. Claude Code loads it when a task matches its description.

How do I install Tbd in Codex?

Run `npx skills add jlevy/strif --skill tbd -a codex`. Or copy the skill folder (.claude/skills/tbd in jlevy/strif) into .agents/skills/tbd in your project. Codex loads it when a task matches its description.

Can I use Tbd 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 jlevy/strif --skill tbd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tbd, .gemini/skills/tbd, .github/skills/tbd and .opencode/skills/tbd in your project.

What does Tbd need to run?

Going by SKILL.md and its folder, Tbd needs the command-line tools its instructions call (npm). Our summary lists: Python 3; Node.js. Its frontmatter pre-approves these tools: Bash(tbd:*), Read, Write.

Does Tbd access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Tbd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tbd use?

Tbd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tbd use?

About 3.5k tokens (SKILL.md is roughly 14k 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 Tbd?

Skills that share tags, products or a category with Tbd: Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Subagent-Driven Development (HoangNguyen0403/agent-skills-standard, 571 stars), Skyvern Version Bump (Skyvern-AI/skyvern, 23k stars) and Git History Bug Audit (ben-manes/caffeine, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tbd?

jlevy (a GitHub user) maintains it in jlevy/strif, which has 131 GitHub stars. The repository was last updated on May 23, 2026.

Source: jlevy/strif on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.