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/aqaddora-report-back
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, testing, writing, productivity
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. 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/report-back
What's inside
- Skill name
report-back- Description
- The mandatory completion-report skill. When an agent finishes (or is blocked on) a handoff bundle or delegated task, it MUST write the outcome to files — never only into chat. Triggers on "I'm done", "this is shipped", "wrap up", "close out this task", "I'm blocked", or automatically at the end of any `handoff-receiver` / `execute` run. Writes a `<bundle>-shipped/handoff.md` report with a fixed schema (commit SHA, what shipped, files touched, test/smoke results, deferred items, new open questions) and sets the source bundle's `manifest.json` status to `shipped · <SHA>` or `blocked · <reason>`. This is the file-based feedback loop that lets a control plane track every agent across tools.
- License
- MIT
- Instructions
- 52 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Report-back
Files in, files out. A delegated agent that reports only in chat is invisible the moment the chat closes. This skill makes the report a durable artifact the orchestrator can read.
## When to Use This Skill
Trigger when the agent:
- Finishes a handoff bundle or delegated task ("done", "shipped", "wrap up", "close out")
- Hits a hard block it can't resolve ("I'm blocked", "stopping here")
- Reaches the end of a `handoff-receiver` or `execute` run (automatic)
## How It Works (3-Step Protocol)
### Step 1 — Write the completion report
Create `<original-bundle>-shipped/handoff.md` next to the source bundle (e.g. `~/Work/AgentHandoffs/2026-05-30-foo-shipped/handoff.md`). Fixed schema:
```markdown
# Shipped — <bundle name>
- Date / agent / tool:
- Commit SHA(s):
- What shipped: (bullet list of concrete changes)
- Files touched: (paths)
- Smoke / test results: (what you ran, what passed)
- Deferred / not done: (with reason)
- New open questions: (for the orchestrator/Ahmed)
- Deploy status: (prepared commands handed to Ahmed / deployed / N/A)
```
### Step 2 — Update the source manifest
Set the source bundle's `manifest.json` `status` to `shipped · <SHA>` or `blocked · <reason>`. This is the single field an orchestrator polls to know state.
### Step 3 — One-line chat summary + pointer
In chat, write one line: what shipped + the report path. Nothing more — the file is the record.
## Operational Rules
1. **Report is mandatory, not optional.** No "done" without a written report.
2. **Status field is the contract.** Always update `manifest.json` status — orchestrators read it, not prose.
3. **Honest blocked > fake shipped.** If tests fail or work is partial, write `blocked` with the reason. Never mark shipped on partial work.
4. **No secrets in reports.** SHAs, paths, results — never tokens, keys, or other-client data.
5. **Don't deploy to report.** If deploy is the user's step, record "commands handed to Ahmed", don't push.
## Position in the PURE Loop
The terminal step after `execute` / `handoff-receiver`. Pairs with `organize-agents`: report-back writes the per-task record; organize-agents indexes runs across tools.
---
*Part of the [Vibe Coding Mastery](https://github.com/AQaddora/vibe-coding-mastery) skill suite. MIT licensed.*From AQaddora/pure-skill-suite, MIT.
More from AQaddora/pure-skill-suite
- 0.519score
understand
AQaddora
Clarifies scope before code is written.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
organize-agents
AQaddora
Maintains a registry of agent runs and outputs across every coding agent the user works with (Claude Code, Cursor, Codex, Aider, Gemini CLI, Windsurf).
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
prime
AQaddora
Builds a tailored primer for an AI coding session — the stack, style, constraints, threat model, and audience that should be loaded BEFORE any real task.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
pure-orchestrator
AQaddora
Runs the full PURE Loop (Prime → Understand → Refine → Execute) on a feature request, calling each phase's skill in sequence with explicit checkpoints for…
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
refine
AQaddora
Runs systematic self-review on AI-generated output before it's accepted.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
doctrine-keeper
AQaddora
Captures insights, rules, and learnings from any AI coding conversation into the user's personal ai-doctrine.md file — a single source of truth that is then…
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
execute
AQaddora
Delegates real work to a coding agent (Claude Code, Cursor agent mode, Codex, Aider) and tracks the run end-to-end.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
handoff
AQaddora
Migrates an in-flight AI coding session to a fresh chat (or a larger-context model) without losing state.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
status-beacon
AQaddora
Lightweight mid-flight progress logging for long agent runs.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
3d-modeler
AQaddora
Generates 3D interior models from photos and injects them into Mapbox GL JS map instances.
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
montage-creator
AQaddora
Generates dynamic video montages and edits video content for social distribution.
SkillCFreshness: C★ 3Claude Code +9 - 0.274score
handoff-receiver
AQaddora
No description from the publisher yet.
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 31, 2026 (5 months ago)
- Last release
- May 31, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/AQaddora/pure-skill-suite
- Website
- aqaddoura.com/blog/pure
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AQaddora
- 0.519score
handoff
AQaddora
Migrates an in-flight AI coding session to a fresh chat (or a larger-context model) without losing state.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
prime
AQaddora
Builds a tailored primer for an AI coding session — the stack, style, constraints, threat model, and audience that should be loaded BEFORE any real task.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
doctrine-keeper
AQaddora
Captures insights, rules, and learnings from any AI coding conversation into the user's personal ai-doctrine.md file — a single source of truth that is then…
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
execute
AQaddora
Delegates real work to a coding agent (Claude Code, Cursor agent mode, Codex, Aider) and tracks the run end-to-end.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
organize-agents
AQaddora
Maintains a registry of agent runs and outputs across every coding agent the user works with (Claude Code, Cursor, Codex, Aider, Gemini CLI, Windsurf).
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
pure-orchestrator
AQaddora
Runs the full PURE Loop (Prime → Understand → Refine → Execute) on a feature request, calling each phase's skill in sequence with explicit checkpoints for…
SkillCFreshness: C★ 3Claude Code +9
Cite this page
report-back skill. Agent Mart. https://agentmart.dev/skills/aqaddora-report-back (last updated 2026-10-24)