shiplog

shiplog is an AI development “skill” that uses Git and GitHub to persist engineering context across sessions by capturing brainstorms as issues, creating isolated work sessions (branches/worktrees), logging commit context, and writing PR “journey” timelines. It also supports cross-model review/provenance/signing conventions, evidence-linked closure, and artifact metadata for later search.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ DevTools ai-agent-skill github-workflow code-review traceability devtools knowledge-graph provenance-signing
⚙ Agent Friendliness
45
/ 100
Can an agent use this?
🔒 Security
44
/ 100
Is it safe for agents?
⚡ Reliability
21
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
55
Error Messages
0
Auth Simplicity
75
Rate Limits
10

🔒 Security

TLS Enforcement
60
Auth Strength
55
Scope Granularity
30
Dep. Hygiene
40
Secret Handling
30

Security posture is partially dependent on the user’s `gh` authentication; no details are provided on token handling within shiplog itself. The workflow persists detailed reasoning/decision context into GitHub issues/PR bodies and a potential `--log` branch, which increases data exposure risk if that content includes sensitive information.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
30
Error Recovery
25
AF Security Reliability

Best When

You want long-term, queryable traceability of “why” behind changes created with AI assistants (Claude Code/Codex/Cursor) and you already use GitHub+gh in a normal repo workflow.

Avoid When

You require an offline-only system with no GitHub writes, or you need fine-grained, auditable permission scoping without using a user’s gh authentication context.

Use Cases

  • Persisting design decisions and rationale for AI-assisted coding across model/sessions
  • Turning brainstorms into searchable GitHub issues with tasks/alternatives
  • Structured work sessions per issue (branches/worktrees) and resumable sessions
  • Cross-model review gates and signed review provenance to reduce self-review
  • Tracking discoveries during work and routing them into inline fixes, stacked PRs, or new issues
  • Evidence-linked closure to avoid closing without proof and to link PR/commit/decision artifacts

Not For

  • Teams that do not use GitHub or cannot use the GitHub CLI (gh)
  • Workflows requiring a strict REST/SDK-only integration without relying on git/gh commands and local repo state
  • Organizations that cannot approve storing decision context in GitHub issues/PR bodies or in a secondary “--log” branch

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

Methods: GitHub CLI (gh) authenticated session
OAuth: No Scopes: No

README states only `gh` CLI is required, authenticated via `gh auth login`. No additional auth mechanisms are described.

Pricing

Free tier: No
Requires CC: No

No pricing information provided in the supplied content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Relies on `gh` CLI and git state (worktrees/branches). Agent use may fail if repo/branch conventions diverge from expectations.
  • Because it writes to GitHub issues/PR bodies and may use a separate `--log` branch, users should ensure appropriate permissions and privacy controls before enabling in sensitive repos.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for shiplog.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered