Install
$ agentstack add skill-jovd83-restassured-skill-session-state ✓ 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Persist Session State
1. Choose The File
- Prefer
docs/testing/session-state.mdin the target repository. - Use
.ai/session-state.mdonly when the repository already stores agent artifacts under.ai/. - Keep one active session-state file per workstream.
2. Start From The Template
- Copy the structure from [session-state-template.md](assets/session-state-template.md).
- Preserve all section headings.
- Replace placeholder text with concrete repo-specific state.
3. Record The Current State
- State the objective in one sentence.
- State the current status, last update time, active owner, and intended next owner.
- State the approved scope and exclusions.
- List the inputs used, including requirements, contracts, tickets, and environments.
- List the files created or changed.
- List the commands already run and their outcomes.
- List completed work.
- List remaining work in execution order.
- List blockers and open questions separately.
- List assumptions and risks explicitly.
4. Make The File Resumable
- Add the exact next command or first next step.
- Add the exact file or class that should be opened next.
- Add the exact verification step still required.
- Add a short
Resume Heresection that another agent can follow without re-reading the full thread.
5. Update It At The Right Times
- Update the file after major implementation steps.
- Update the file after each new test slice, coverage artifact, or contract-analysis expansion.
- Update the file before handing work back to a human.
- Update the file before stopping with blockers or unresolved failures.
- Update the file after changing scope, assumptions, or contracts.
- Update the file after every verification run that changes the known result, even when the run fails.
6. Keep It Honest
- Do not mark work complete unless the relevant files exist.
- Do not claim verification unless the command was actually run.
- Do not hide blockers inside assumptions.
- Do not delete unresolved questions; move them into the open-questions section.
- Do not let the session-state lag behind the actual scope by more than one major work item.
7. Examples
- Input:
Leave a checkpoint so another agent can resume the payments API work.
Output: Create or update docs/testing/session-state.md with completed files, failed and pending commands, blockers, and the next exact step.
- Input:
Summarize where you left off after this contract-analysis pass.
Output: Update the session-state artifact with the analyzed contracts, unresolved mismatches, and the next coverage-planning step.
8. Troubleshooting
- Problem: The repository already has multiple ad hoc status files.
Fix: Consolidate the active state into one canonical session-state file and link older notes under Inputs Used or History.
- Problem: The next agent cannot tell what was verified.
Fix: Add exact commands and outcomes under Verification Run.
- Problem: The work stopped because of a human decision.
Fix: Put the decision request under Blockers and repeat it in Resume Here.
- Problem: The session-state still reflects an earlier slice after new tests or docs were added.
Fix: Reconcile Scope, Files Created Or Changed, Verification Run, and Remaining Work immediately before stopping.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jovd83
- Source: jovd83/restassured-skill
- License: MIT
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.