Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/aaronsb/claude-code-config/shipnpx skills add aaronsb/claude-code-config --skill shipgit clone --depth 1 https://github.com/aaronsb/claude-code-configWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00051 | $0.01276 |
| Opus 5 | $0.00026 | $0.00638 |
| Sonnet 5 | $0.00010 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship Workflow
Deliver current work to main. Assess the current state and pick up from wherever the user is.
Arguments
/ship— default flow, adapts review gate to repo flavor/ship full-sail— skip the review pause (solo/pair repos only; team repos still pause)
Assess First
Run these in parallel to determine current position in the flow:
git status --short # Uncommitted changes?
git branch --show-current # On main or a feature branch?
git log --oneline main..HEAD # Commits ahead of main?
git remote show origin 2>&1 # Remote tracking state?
Also check repo flavor for review gating:
# Active contributors in last 90 days
git log --since="90 days ago" --format='%aN' | sort -u | wc -l
- ≤2 active: Solo/pair — lightweight PRs, review pause optional
- 3+ active: Team — review pause mandatory, suggest reviewers
If the GitHub way has already injected context (look for **Context**: Team project or
**Context**: Solo/pair project in the conversation), use that instead of re-checking.
Flow Steps (skip what's already done)
1. Branch (if on main with changes)
git checkout -b <branch-name>
Pick a name from the changes: feature/thing, fix/thing, refactor/thing.
If the user provides a name, use it. If changes are already committed on main,
create the branch first, then it carries the commits.
2. Commit (if uncommitted changes)
Stage and commit. Follow conventional commit format. If there are multiple logical changes, make multiple atomic commits. Ask the user for a commit message direction if the intent isn't clear.
3. Push
git push -u origin <branch>
4. PR
gh pr create --title "..." --body "$(cat <<'EOF'
## Summary
...
## Test plan
...
EOF
)"
Keep the title under 70 characters. Summary should be 1-3 bullets. For small/obvious changes, the test plan can be brief.
5. Review Gate
Team repos (3+ active contributors):
- Always pause here. State the change scope and suggest reviewers.
- Do NOT proceed to merge without explicit user approval.
- Exception:
/ship full-sailis rejected for team repos — tell the user why.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 163 lines · 51 tokens per session scan A c6259c5c0fc8
ship is a skill published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,276 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
achieving-cmmc-level-2-compliance
Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when…
task-planning-arch
计算任务 gap 并产出下一步可执行子任务 List[TaskSpec];gap 已闭返回空数组。对齐 arch 场景(架构师名册/技术栈概览/双视角分析)确定式分解——按根目标交付物集合 + donechildren 查表(参照 task-planning storage 特例,非自由 LLM 分解)。.
task-search
在框架预查的候选 bot 集里决出执行者(who)与协作方式(how),返回 4 态 SearchResult(HITSINGLE/HITGROUP/HITMULTIBOTS/MISS)。对齐案例剧本确定式映射。.
escalation-governance
Assess whether to escalate models. Use when evaluating reasoning depth.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
silicon-throne
硅基圣座总控核心，以神谕式统御把零散任务压成 末将-first 之文明工程.