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.
Technical briefing for developer sharing. An agent skill from sd0xdev/sd0x-harness.
Install Tech Brief
$ npx skills add sd0xdev/sd0x-harness --skill tech-brief -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sd0xdev/sd0x-harness tech-brief --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/sd0xdev/sd0x-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tech-brief .claude/skills/tech-brief && 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 "tech-brief" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/tech-brief into .claude/skills/tech-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tech-brief", 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/sd0xdev/sd0x-harness/tree/main/skills/tech-briefType 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 sd0xdev/sd0x-harness --skill tech-brief -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sd0xdev/sd0x-harness tech-brief --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tech-brief .agents/skills/tech-brief && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tech-brief" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/tech-brief into .agents/skills/tech-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tech-brief", 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 sd0xdev/sd0x-harness --skill tech-brief -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sd0xdev/sd0x-harness tech-brief --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tech-brief .cursor/skills/tech-brief && 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 "tech-brief" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/tech-brief into .cursor/skills/tech-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tech-brief", 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/sd0xdev/sd0x-harness.git --path skills/tech-brief--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 sd0xdev/sd0x-harness --skill tech-brief -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sd0xdev/sd0x-harness tech-brief --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tech-brief .gemini/skills/tech-brief && 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 "tech-brief" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/tech-brief into .gemini/skills/tech-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tech-brief", 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 sd0xdev/sd0x-harness tech-briefInstalls 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 sd0xdev/sd0x-harness --skill tech-brief -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tech-brief .github/skills/tech-brief && 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 "tech-brief" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/tech-brief into .github/skills/tech-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tech-brief", 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 sd0xdev/sd0x-harness --skill tech-brief -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sd0xdev/sd0x-harness tech-brief --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tech-brief .opencode/skills/tech-brief && 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 "tech-brief" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/tech-brief into .opencode/skills/tech-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tech-brief", 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
tech-brief- GitHub stars
- 192
- Token cost
- ~2k tokens
- SKILL.md length
- 616 words
- Files
- 3 (incl. references)
- Skills in repo
- 91
- Repo updated
- First seen
- Licence
- MIT
At a glance
Technical briefing for developer sharing. An agent skill from sd0xdev/sd0x-harness.
- Works in 4 steps: Context Resolution → Multi-Source Collection → Synthesis → …
- : sharing implementation findings with technical colleagues
- SKILL.md covers Trigger, When NOT to Use, Command Signature and Workflow, plus 6 more sections
- Calls git and node
What it does
Tech Brief is an agent skill from sd0xdev/sd0x-harness. Technical briefing for developer sharing. Use when: sharing implementation findings with technical colleagues, post-development knowledge transfer, documenting what was built and why. Not for: PM/CTO summary (use project-brief), first-principles reasoning (use fp-brief), design-phase specs (use tech-spec). Output: 6-section technical brief with source provenance.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/output-template.md` and `references/source-guide.md`).
It sits in Development. The repository describes itself as: The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and… The licence is MIT.
When your agent uses it
- : sharing implementation findings with technical colleagues
- Post-development knowledge transfer
- Documenting what was built and why
Example prompts
- “/tech-brief”
Requirements
- Pre-approved tools (allowed-tools): Read, Grep, Glob, Write, Bash(git:*), Bash(node:*)
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit c9a2036. 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:
ReadGrepGlobWriteBash(git:*)Bash(node:*)
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
gitnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, 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
Tech Brief loads about 2k tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 616 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 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 sd0xdev/sd0x-harness at commit c9a2036, republished under its MIT licence (© sd0xdev). 616 words, ~1,962 tokens.
Download SKILL.mdSave it as
.claude/skills/tech-brief/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- tech-brief
- description
- Technical briefing for developer sharing. Use when: sharing implementation findings with technical colleagues, post-development knowledge transfer, documenting what was built and why. Not for: PM/CTO summary (use project-brief), first-principles reasoning (use fp-brief), design-phase specs (use tech-spec). Output: 6-section technical brief with source provenance.
- allowed-tools
- Read, Grep, Glob, Write, Bash(git:*), Bash(node:*)
Technical Briefing Skill
Trigger
- Keywords: tech brief, technical briefing, share with team, tech-brief, dev sharing, share findings, technical memo
When NOT to Use
| Scenario | Alternative |
|---|---|
| PM/CTO executive summary (strip technical details) | /project-brief |
| First-principles reasoning chain (why decisions were made) | /fp-brief |
| Design-phase technical specification (before implementation) | /tech-spec |
| Code explanation at function/file level | /codex-explain |
| Simple document summary | Ask Claude directly |
Command Signature
/tech-brief [<feature-key>|<docs-path>] [--depth brief|normal|deep] [--output <path>] [--no-save]| Flag | Default | Description |
|---|---|---|
<feature-key> | Auto-detect | Feature key or docs path |
--depth | normal | Output depth (brief/normal/deep) |
--output | docs/features/<key>/5-tech-brief.md | Custom output path |
--no-save | false | Print to stdout only |
Workflow
sequenceDiagram
participant U as User
participant S as /tech-brief
participant FR as feature-resolver.js
participant D as Feature Docs
participant G as Git History
participant C as Changed Files
participant O as Output File
U->>S: /tech-brief [feature] [--depth] [--output]
Note over S: Phase 1: Context Resolution
S->>FR: Resolve feature (5-level cascade)
FR-->>S: Feature key + doc inventory
Note over S: Phase 2: Multi-Source Collection
S->>D: Stage 1 — Read docs (tech-spec, architecture, requests)
S->>G: Stage 2 — git log + diff + changed file reading
S->>D: Stage 3 — Request selection (top 3 by date)
Note over S: Phase 3: Synthesis
S->>S: Build Source Provenance table
S->>S: Extract & organize by output template
S->>S: Apply depth filter
Note over S: Phase 4: Output
S->>O: Write tech-brief file
S-->>U: Report completePhase 1: Context Resolution
- Parse
$ARGUMENTSfor feature-key, path, or flags - Resolve feature using
node scripts/resolve-feature.js [--feature <key>]— the wrapper, not the CLI: it owns the failure payload. Ifscan_error !== false— including a payload with no such field, which is what a shell|| echo '{}'fallback produces — the four source sets are unknown, not empty. Stop and take the ⚠️ Need Human exit; a non-nullkeyis not evidence the sets are complete - Load
doc_inventoryand the four source sets from resolver output - Validate paths (see Path Security)
Input Resolution Table
| Input Type | Example | Feature Resolution | Default Output Path |
|---|---|---|---|
| Feature key | /tech-brief fp-brief | --feature fp-brief | docs/features/fp-brief/5-tech-brief.md |
| Feature dir | /tech-brief docs/features/fp-brief/ | Extract key from path | docs/features/fp-brief/5-tech-brief.md |
| Feature doc | /tech-brief docs/features/fp-brief/2-tech-spec.md | Extract key from parent | docs/features/fp-brief/5-tech-brief.md |
| Non-feature | /tech-brief /tmp/notes.md | No feature context | Require --output |
| No argument | /tech-brief | Auto-detect (5-level cascade) | Based on resolved feature |
Phase 2: Multi-Source Collection
Three-stage collection. See references/source-guide.md for detailed strategy.
Stage 1 — Document Collection: Read design_records (tech-spec, architecture, feasibility) for the why and current_authority for the what it does now. All optional — and a brief that presents a design record's claim as shipped behaviour is the failure mode to avoid; Stage 2's code evidence is what settles the difference.
Stage 2 — Code & Git Evidence: git log -20, git diff --stat, read top 5 changed source files (100 lines each) for file:line references.
Stage 3 — Request Selection: Glob all request docs (no status filter — completed features are the primary use case), max 3 by date desc. Extract ## References for threadIds and PR links.
Phase 3: Synthesis
- Build Source Provenance table (Section | Source Files | Confidence)
- For each output section, extract content from mapped sources (see
references/output-template.md) - Apply depth filter (section inclusion and detail level per depth matrix)
- Apply Evidence Insufficient Rule:
[Source unavailable — no <type> found for this feature]
Show full SKILL.md (223 more words)Show less
Phase 4: Output
See Save Behavior for output path resolution.
Path Security
- Path normalization: Resolve
..and symlinks, verify repo boundary - Traversal rejection: Input containing
..is rejected - Output path:
--outputallows repo-external paths (e.g./tmp/), emit warning "writing outside repo" - Secret redaction: Before reading source docs, scan for high-confidence secret patterns (API keys, private keys) — high confidence: abort; medium confidence: mask
[REDACTED]
Depth Levels
| Level | Max Length | Description |
|---|---|---|
| brief | ~500 words | Key points only — suitable for Slack sharing |
| normal | ~1500 words | Full coverage with source citations |
| deep | ~3000 words | Full coverage + code snippets + alternative comparison |
These are upper bounds, not targets. Source-thin features will produce shorter output.
Output
See references/output-template.md for full template and depth matrix.
# Tech Brief: <Feature Title>
> Feature: <key> | Depth: <level> | Generated: <timestamp>
> Sources: <list of docs read>
## Source Provenance
| Section | Source Files | Confidence |
## 1. Background & Problem
## 2. Design Decisions & Trade-offs
## 3. Implementation Highlights
## 4. Limitations & Known Issues
## 5. Discussion & References
## 6. Next StepsSave Behavior
| Condition | Output Path |
|---|---|
| Default (feature resolved) | docs/features/<key>/5-tech-brief.md |
--output <path> | Specified path (warn if outside repo) |
--no-save | stdout only, no file written |
No feature + no --output | Gate: Need Human |
Preferred canonical name: 5-tech-brief.md. If 5- prefix is occupied, use next available number.
Verification
- Feature context resolved (5-level cascade or explicit)
- Path validation executed (no traversal, repo boundary)
- Secret redaction scan completed
- Source Provenance table present in output
- Each section cites source (or shows Missing Source marker)
- Output length within depth-level upper bound
- Evidence Insufficient markers used where source is thin
References
- Output template:
references/output-template.md - Source collection guide:
references/source-guide.md - Feature context resolution:
@skills/create-request/references/feature-context-resolution.md
Examples
Input: /tech-brief seek-verdict
Action: Resolve feature → read tech-spec + request → git log → write 5-tech-brief.md
Input: /tech-brief --depth brief --output /tmp/sharing.md
Action: Auto-detect feature → collect sources → brief output → write /tmp/sharing.md
Input: /tech-brief docs/features/auto-loop-evolution/ --depth deep
Action: Extract key → read all docs + requests (top 3) → deep output with code snippets
Input: /tech-brief --no-save
Action: Auto-detect → collect → print to stdout (no file)© sd0xdev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/tech-brief of sd0xdev/sd0x-harness.
- SKILL.md
- references/output-template.md
- references/source-guide.md
Open the folder on GitHubat commit c9a2036
Compare with similar skills
Tech Brief 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 |
|---|---|---|---|---|---|---|
| Tech Brief this skillsd0xdev/sd0x-harness | 192 | — | ~2k | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 24 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 | |
| Greplooponyx-dot-app/onyx | 32k | 4 repos | ~3.3k | Automated safety check: Pass | MIT |
Similar skills
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.
Guidelines
akash-network/node
Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.
More from sd0xdev/sd0x-harness
All 91 skills in this repoAdr
sd0xdev/sd0x-harness
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as docs/features/<feature/adr-<NNN-<title.md with a 3-digit zero-padded…
Load PR Review
sd0xdev/sd0x-harness
Load GitHub PR review comments into AI session — analyze, triage, plan.
Next Step
sd0xdev/sd0x-harness
Change-aware next step advisor. An agent skill from sd0xdev/sd0x-harness.
Obsidian CLI
sd0xdev/sd0x-harness
Obsidian vault integration via official CLI. An agent skill from sd0xdev/sd0x-harness.
Orchestrate
sd0xdev/sd0x-harness
Agent-driven workflow orchestration (v1 report-only). An agent skill from sd0xdev/sd0x-harness.
PR Comment
sd0xdev/sd0x-harness
Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review.
Related
Categories
Questions about Tech Brief
What does Tech Brief do?
Technical briefing for developer sharing. An agent skill from sd0xdev/sd0x-harness. Tech Brief is an agent skill from sd0xdev/sd0x-harness. Technical briefing for developer sharing.
When should I use Tech Brief?
Tech Brief fits situations like: : sharing implementation findings with technical colleagues; post-development knowledge transfer; documenting what was built and why.
How do I install Tech Brief in Claude Code?
Run `npx skills add sd0xdev/sd0x-harness --skill tech-brief -a claude-code`. Or copy the skill folder (skills/tech-brief in sd0xdev/sd0x-harness) into .claude/skills/tech-brief in your project. Claude Code loads it when a task matches its description.
How do I install Tech Brief in Codex?
Run `npx skills add sd0xdev/sd0x-harness --skill tech-brief -a codex`. Or copy the skill folder (skills/tech-brief in sd0xdev/sd0x-harness) into .agents/skills/tech-brief in your project. Codex loads it when a task matches its description.
Can I use Tech Brief 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 sd0xdev/sd0x-harness --skill tech-brief -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tech-brief, .gemini/skills/tech-brief, .github/skills/tech-brief and .opencode/skills/tech-brief in your project.
What does Tech Brief need to run?
Going by SKILL.md and its folder, Tech Brief needs the command-line tools its instructions call (git and node). Its frontmatter pre-approves these tools: Read, Grep, Glob, Write, Bash(git:*), Bash(node:*).
Does Tech Brief access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Tech Brief 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 Tech Brief use?
Tech Brief 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 Tech Brief use?
About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.
What are the alternatives to Tech Brief?
Skills that share tags, products or a category with Tech Brief: Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars) and Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tech Brief?
sd0xdev (a GitHub user) maintains it in sd0xdev/sd0x-harness, which has 192 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on October 6, 2026.
Source: sd0xdev/sd0x-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.