Skills session-handoff
📦

session-handoff

Content revision r1 Medium Risk 📁 Filesystem access⚙️ External commands🌐 Network access🔑 Env variables

Create Reliable AI Session Handoffs

Long AI coding sessions lose context when a session ends. This skill creates structured handoffs so Claude, Codex, or Claude Code can resume with clear next steps.

Supports: Claude Codex Code(CC)
⚠️ 50 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "session-handoff" from https://skillstore.io/skills/softaworks-session-handoff.md and its manifest at https://skillstore.io/api/skills/softaworks-session-handoff/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/softaworks-session-handoff.md Signed manifest GET /api/skills/softaworks-session-handoff/manifest Signed lockfile GET /api/skills/softaworks-session-handoff/lockfile

Test it

Using "session-handoff". Create a handoff for this authentication refactor.

Expected outcome:

Creates a timestamped handoff with session metadata, current state, completed work, pending tasks, decisions, and environment notes.

Using "session-handoff". Resume from the most recent handoff.

Expected outcome:

Lists available handoffs, checks staleness, reads the selected handoff, and identifies the first verified next step.

Using "session-handoff". Validate this handoff before I stop.

Expected outcome:

Reports quality score, remaining placeholders, missing required sections, possible secrets, and broken file references.

Security Audit

Medium Risk
v4 • 7/7/2026 Open versioned report

Static analysis produced many command, filesystem, environment, and network matches. Review confirmed only the evaluation cleanup deletion risk plus contextual handoff data-handling risks; most high signals are test fixtures, Markdown examples, defensive secret patterns, or shell-free hardcoded git calls. No bundled prompt injection attempt or data exfiltration behavior was found.

12
Files scanned
2,721
Lines analyzed
2
Review items
0
False positives ignored

Confirmed security concerns (3)

Medium
SKILL.md:41-43scripts/create_handoff.py:230-336scripts/validate_handoff.py:22-37
Persistent Handoff Files May Preserve Sensitive Context
The skill creates Markdown handoffs that can include project path, branch, commits, modified files, decisions, and environment variable names. Secret scanning helps, but handoffs may still preserve sensitive implementation or business context.
The storage behavior and metadata capture are explicit in the workflow and generated template. The risk depends on what users write into handoffs, so this is a data-handling concern rather than malicious collection.
Medium
SKILL.md:116-134references/resume-checklist.md:7-17
Untrusted Handoff Content Can Influence Agent Behavior
The resume workflow tells the agent to read a handoff and begin from its documented next steps. Handoff files imported from a repository can contain instructions that should be treated as untrusted project context.
The workflow consumes Markdown handoffs as operational context. No bundled prompt-injection payload was found, but the trust boundary should be documented for imported handoffs.
Low
references/resume-checklist.md:56-66
Resume Checklist Encourages Local Environment Inspection
The quick-start checklist suggests commands that can reveal process details or environment variable names. This is useful for verification, but outputs should be minimized and redacted.
The checklist explicitly includes git, process, and environment inspection commands. The commands are local and visible, so the risk is limited to accidental disclosure in transcripts or handoffs.
Capability review items (2)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
evals/setup_test_env.py:41
Python shutil operations
shutil.rmtree(path)
The evaluation setup script recursively deletes the configured target path before creating fixtures. The default is a temp directory, but a user-supplied path could cause local data loss if misused.
Medium
evals/setup_test_env.py:379
Python shutil operations
shutil.rmtree(path)
The --clean path removes the configured test environment with shutil.rmtree. The action is explicit, but the script should guard against accidental deletion outside the intended temp fixture path.

Risk Factors

📁 Filesystem access (15)
evals/model-expectations.md:154 evals/results-opus-baseline.md:73 evals/results-opus-baseline.md:56 evals/results-opus-baseline.md:83 evals/setup_test_env.py:11 evals/setup_test_env.py:23 evals/setup_test_env.py:149 evals/setup_test_env.py:41 evals/setup_test_env.py:379 evals/test-scenarios.md:15 evals/test-scenarios.md:16 scripts/create_handoff.py:122 scripts/list_handoffs.py:77 scripts/list_handoffs.py:106 scripts/list_handoffs.py:110
⚙️ External commands (29)
evals/setup_test_env.py:29 scripts/check_staleness.py:28 scripts/create_handoff.py:32 scripts/create_handoff.py:332 scripts/validate_handoff.py:110 scripts/validate_handoff.py:115 SKILL.md:29-31 SKILL.md:31-33 SKILL.md:33-36 SKILL.md:36-38 SKILL.md:38-41 SKILL.md:41-49 SKILL.md:49-62 SKILL.md:62-64 SKILL.md:64-67 SKILL.md:67-89 SKILL.md:89-91 SKILL.md:91-99 SKILL.md:99-101 SKILL.md:101-146 SKILL.md:146-152 SKILL.md:152-158 SKILL.md:158-169 SKILL.md:169-171 SKILL.md:171-173 SKILL.md:173-181 SKILL.md:181-182 SKILL.md:182-183 SKILL.md:183-184
🌐 Network access (1)
evals/setup_test_env.py:270
🔑 Env variables (9)
evals/setup_test_env.py:79 evals/setup_test_env.py:89 evals/setup_test_env.py:79 evals/setup_test_env.py:89 evals/setup_test_env.py:89 evals/setup_test_env.py:197 evals/setup_test_env.py:266 evals/setup_test_env.py:320 evals/setup_test_env.py:331
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/softaworks-session-handoff/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/softaworks-session-handoff/security.svg)](https://skillstore.io/skills/softaworks-session-handoff?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/softaworks-session-handoff?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/softaworks-session-handoff/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/softaworks-session-handoff.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

softaworks. (2026). session-handoff security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/softaworks-session-handoff/audits/4

BibTeX citation

@techreport{softaworks-softaworks-session-handoff-2026, author = {softaworks}, title = {session-handoff security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/softaworks-session-handoff/audits/4}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "session-handoff security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "softaworks" date-released: "2026-07-07" url: "https://skillstore.io/skills/softaworks-session-handoff/audits/4" identifiers: - type: other value: "skillstore:softaworks-session-handoff:audit:4" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
77
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance

What You Can Build

Pause a Long Coding Task

Capture current state, modified files, decisions, blockers, and immediate next steps before ending a session.

Resume Work From a Previous Agent

Find the latest handoff, check if it is stale, and continue from the documented next action.

Maintain Context Across Milestones

Create chained handoffs after major milestones so future sessions can trace decisions and progress.

Try These Prompts

Create a Basic Handoff 
Create a handoff for the current work session. Include current status, modified files, decisions, blockers, and next steps.
Validate a Handoff 
Validate the handoff file and summarize any TODOs, missing sections, stale references, or possible secrets.
Resume From the Latest Handoff 
Find the latest handoff, check staleness, read it fully, and tell me the first safe action to take.
Chain a Milestone Handoff 
Create a continuation handoff linked to the previous one. Emphasize new decisions, completed tasks, changed assumptions, and next risks.

Best Practices

  • Run validation before sharing or committing a handoff.
  • Record environment variable names only, never secret values.
  • Review imported handoffs for untrusted instructions before following them.

Avoid

  • Do not store API keys, tokens, passwords, or private keys in handoffs.
  • Do not resume from a stale handoff without checking current git state.
  • Do not leave vague TODOs where the next agent needs concrete actions.

Frequently Asked Questions

Where are handoff files stored?
The skill stores generated handoffs in .claude/handoffs within the current project.
Does this skill send data to a remote service?
No runtime network call was found in the reviewed scripts. The skill operates on local files and git metadata.
Can it detect secrets in handoffs?
It checks common secret patterns such as API keys, passwords, tokens, and private key markers.
Can it resume work automatically?
It provides context and a checklist for resumption. The agent should still verify current project state first.
Does it require git?
Git is not required for all features, but branch, commit, and staleness checks depend on git.
Is it safe to publish handoffs?
Only publish reviewed handoffs. They may contain project paths, commit messages, file names, and sensitive context.

Developer Details

Author

softaworks

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/softaworks/agent-toolkit/tree/main/skills/session-handoff/

Ref

f93e9bb0daca99badb6a7e574b97737155d57cb3

Maintenance freshness

7/18/2026

Usage

35 downloads · 226 views

File structure

📁 evals/

📄 model-expectations.md

📄 results-opus-baseline.md

📄 setup_test_env.py

📄 test-scenarios.md

📁 references/

📄 handoff-template.md

📄 resume-checklist.md

📁 scripts/

📄 check_staleness.py

📄 create_handoff.py

📄 list_handoffs.py

📄 validate_handoff.py

📄 README.md

📄 SKILL.md

More from softaworks

View all

Related Skills

View all