Atlas / Skills / davepoon / Resume Work

Resume WorkSAFE

skills/davepoon/resume-work

A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
—
License
MIT
Stars
3,604
01

Overview

A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw

Read from source at commit 80a0afd96301OBSERVED · 2026-10-07
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: gsd:resume-work
description: Resume work from previous session with full context restoration
allowed-tools:
  - Read
  - Bash
  - Write
  - AskUserQuestion
  - SlashCommand
---

<objective>
Restore complete project context from a previous session — handling both manual pause (from `/gsd:pause-work`) and auto-compact (from the PreCompact hook) handoffs identically.
</objective>

<process>

1. **Detect handoff state.**
   Check for `.planning/HANDOFF.json` via Read tool. If missing, the session has no handoff — announce "No handoff found" and proceed to normal `/gsd:progress` routing.

2. **Load STATE.md.**
   Read `.planning/STATE.md` to restore the big-picture project position. If missing, reconstruct from `.planning/ROADMAP.md` and the latest phase directory's SUMMARY.md files; if reconstruction fails, surface the error and stop.

3. **Read the handoff.**
   Parse `.planning/HANDOFF.json`. Extract phase, plan, task, status, source, uncommitted_files, decisions, context_notes, next_action. Per HANDOFF schema, all fields are always present (empty arrays / null for unset).

4. **Present project status.**
   Emit a compact status block covering:
   - Milestone + percent complete (from STATE.md frontmatter `progress.percent`).
   - Current phase name and number.
   - Plan / task position from the handoff.
   - Handoff source (manual-pause vs auto-compact) and timestamp.
   - Top 3 decisions and any blockers from the handoff.
   - Uncommitted files summary.
   - The `next_action` string verbatim — it's the resumption hint.

5. **Route to the next action.**
   Offer 1-3 concrete options based on handoff state. Common patterns:
   - If task was mid-execute: offer `/gsd:execute-phase` with the current phase.
   - If phase is at plan boundary: offer `/gsd:plan-phase` or `/gsd:execute-phase` for the next phase.
   - If there are uncommitted files that look in-progress: call attention to them before offering continuation.

6. **Clean up the handoff (LIFE-01).**
   After routing — once steps 1-5 have completed without error — remove the handoff file:

   ```bash
   node "${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/cache/gsd-plugin/current}/bin/gsd-tools.cjs" checkpoint --clear
   ```

   If the command is unavailable for any reason, fall back to direct removal:
   ```bash
   rm -f .planning/HANDOFF.json
   ```

   Do not abort the resume if cleanup fails — it's hygiene, not correctness. The next session's SessionStart will overwrite a stale handoff anyway (per D-05 from Phase 4: latest snapshot wins).

</process>

<rules>
- Step 6 runs **last**, after all context is loaded and the user has been shown status. A failed/aborted resume (steps 1-5 error out) leaves HANDOFF.json on disk for recovery (per D-08).
- If `HANDOFF.json` is absent in step 1, skip everything — don't attempt to clean up what isn't there. `checkpoint --clear` is idempotent but unnecessary work.
- The skill is the single owner of HANDOFF.json deletion. The SessionStart hook must NOT delete — it only detects (per D-10).
</rules>
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 80a0afd96301full audit observations/trust-audit/skill/davepoon__resume-work.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-0780a0afd96301SAFEB89first audit
05

Questions

What does the Resume Work skill do?

A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw

Is Resume Work safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Resume Work access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (80a0afd96301), read on 2026-10-07. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement