# Brief Report

> Use when a sub-session has finished its delegated task and needs to write a results brief for the parent session to pick up — captures what was done, what worked, what didn't, and any new blockers the parent should know about. Triggered after completing a task that was started from a `brief-delegate` brief, or when the user says "write a report brief", "I'm done — brief back".

- **Type:** Skill
- **Install:** `agentstack add skill-useaitechdad-agent-skills-brief-report`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [useaitechdad](https://agentstack.voostack.com/s/useaitechdad)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [useaitechdad](https://github.com/useaitechdad)
- **Source:** https://github.com/useaitechdad/agent-skills/tree/main/brief_skills_agent_skill/brief-report

## Install

```sh
agentstack add skill-useaitechdad-agent-skills-brief-report
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# brief-report — report results back to the parent session

You are a sub-session that finished its delegated task. Write a results brief the **parent** session will read to continue.

## Where to save

```
~/.claude/projects//briefs/brief-.md
```

Compute the paths yourself — no shell needed for the slug:

- `` = current working directory with every `/` replaced by `-` (e.g. cwd `/Users/you/code/myapp` → slug `-Users-you-code-myapp`). You already know the cwd from your environment.
- briefs dir = `/.claude/projects//briefs` (absolute, your real home path).

You **do** need one shell call — the timestamp, since Claude has no clock:

```bash
date +%Y-%m-%d-%H%M%S   # local time — keeps the filename stamp consistent with the log stamp
```

The filename is `brief-.md`. Write it with the **Write** tool (it creates the briefs dir if missing) — don't shell out to create the file.

## What to write

Aim for ~15-30 lines. Concrete outcomes, not retelling.

```markdown
# Brief — 

**Flavor**: report
**Created**: 
**Project**: 
**Responds to**: .md`). You read it to start this work, so you know its path. Never leave blank.>

## Outcome

## What changed
- 
- 

## What worked
- 

## What didn't / blockers
- 

## Loose ends
- 
```

## After writing

1. Append the log entry via the shared helper (owns the format + trim + file pruning — don't hand-format the line). Pass the absolute briefs dir and the file you just wrote:
   ```bash
   ~/.claude/skills/_brief-shared/append-log.sh "" report "" ""
   ```
2. Print the file path.
3. One-line hint: "In the parent session, run `/brief-resume` and pick this entry."

## What NOT to include

- Don't try to solve loose ends here — **flag them; let the parent decide**.
- Don't include speculative plans for what to do next — only what actually happened.
- Don't include reasoning chains or rejected alternatives.
- Don't gloss over partial completion as "done" — be honest.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [useaitechdad](https://github.com/useaitechdad)
- **Source:** [useaitechdad/agent-skills](https://github.com/useaitechdad/agent-skills)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-useaitechdad-agent-skills-brief-report
- Seller: https://agentstack.voostack.com/s/useaitechdad
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.