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/derjochenmeyer/claude-code-craft/craft-session-solidifynpx skills add derjochenmeyer/claude-code-craft --skill craft-session-solidifygit clone --depth 1 https://github.com/derjochenmeyer/claude-code-craftWhat 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 | $0.00064 | $0.01615 |
| Opus 5 | $0.00032 | $0.00807 |
| Sonnet 5 | $0.00013 | $0.00323 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
craft-session-solidify 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft-session-solidify
Save the current state — then keep working.
When to run
- Automatic: when the context monitor reports ~75% utilization
- Manual: when the user types
/craft-session-solidify - Proactive: when you notice a lot has happened that is not yet documented and the context window is filling up
Scope — what does NOT belong here
This skill maintains project documentation in .craft/. It does not maintain Claude's own memory. The boundary:
| Tool | Purpose | Target |
|---|---|---|
/craft-session-solidify |
Project state, backlog, decisions, handover | .craft/*.md |
/remember |
Save a single fact, decision, or warning | .claude/memory/YYYYMMDD_*.md |
/learn |
Abstract a pattern from context into a transferable insight | .claude/memory/YYYYMMDD_*.md |
Concretely: do not write new .claude/memory/ entries from this skill. If you notice during the solidify that a fact or pattern is worth keeping — mention it in the closing report as a recommendation (worth a /remember or worth a /learn), but do not write it yourself.
.craft/DECISIONS.md (project-level ADR log) and .claude/memory/ entries with type=decision (Claude's personal memory) are deliberately different layers. Some duplication is fine, but it is not the goal of this skill.
Steps
1. Get an overview
git diff --stat HEAD 2>/dev/null
git status --short 2>/dev/null
git log --oneline -5 2>/dev/null
ls .craft/ 2>/dev/null || echo "no .craft/"
If there is no .craft/: run anyway, but skip the doc-writing steps. Commit and short report still happen. At the end, suggest running /craft-project-setup.
2. Update .craft/PROJECT_STATE.md
Prepend a section at the top (newest state first):
## State: [YYYY-MM-DD HH:MM]
### Working
- ...
### In progress
- ...
### Known issues
- ...
### Technical debt
- ...
Be honest. If something is not working, say so explicitly — do not omit.
3. Update .craft/BACKLOG.md
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 · 192 lines · 64 tokens per session scan A f3bddde3128c
craft-session-solidify is a skill published in the GitHub repository derjochenmeyer/claude-code-craft (2 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,615 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…