— No reviews yet
0 installs
11 views
0.0% view→install
Install
$ agentstack add skill-markoblogo-abvx-agent-skills-delivery-baseline-audit ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Are you the author of Delivery Baseline Audit? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claimAbout
Delivery Baseline Audit
Verify that the promised deliverables actually exist relative to where the work started.
Use When
- the task names files, features, screens, commands, or other concrete deliverables;
- the implementation ran through multiple phases or retries;
- the working tree may contain staged, unstaged, or untracked work that matters;
- "agent said done" is not enough evidence.
Core Rules
- Compare against the starting baseline, not just the latest transcript claim.
- Check the whole working tree, not only committed diffs.
- Re-run final mandatory commands once at the end for cross-phase regressions.
- Treat missing deliverables as a gap even if the narrative sounds complete.
Workflow
- Capture or identify the baseline reference before major work starts.
- List the declared deliverables and acceptance criteria.
- At the end, inspect the full working tree relative to that baseline:
- committed changes;
- staged changes;
- unstaged changes;
- deletions;
- untracked deliverables.
- Re-run the final mandatory verification commands.
- Spot-check each deliverable against its declared acceptance criteria.
- Report gaps explicitly and fix them before calling the task complete.
Audit Output
Include:
- baseline reference used;
- deliverables checked;
- commands re-run;
- gaps found;
- fix-needed or complete verdict.
Anti-Patterns
- Do not audit only what was committed if the working tree still matters.
- Do not rely on a prior mid-task pass as the final audit.
- Do not mark complete when a declared deliverable is absent or unverifiable.
Final Report
State whether completion was confirmed against baseline, partially confirmed, or blocked by missing evidence.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: markoblogo
- Source: markoblogo/abvx-agent-skills
- License: MIT
- Homepage: https://abvx.xyz/work/abvx-agent-skills
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.