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 commands/codeverbojan/claude-code-kickstart/wrap-upgit clone --depth 1 https://github.com/codeverbojan/claude-code-kickstartWhat 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 | $0.00013 | $0.00542 |
| Opus 5 | $0.00006 | $0.00271 |
| Sonnet 5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade B, and why
wrap-up scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `signals_captured`: `grep -c "$(date -u +%Y-%m-%d)" .claude/signals.jsonl 2>/dev/null || echo 0` What it actually says
Session Wrap-Up
1. Verify
Run typecheck/lint/tests if any code changed. Note pass/fail. Skip if nothing was touched.
2. Rewrite primer.md
Overwrite primer.md with exactly this structure (replace bracketed hints):
# Session Primer
## Last Session
[date]: [1–2 sentence summary]
## What Changed
- [file]: [why]
## Current State
[what works, what doesn't, what's partial]
## Uncommitted Changes
[list, or "None"]
## Test Status
- Type-check: PASS | FAIL | NOT CONFIGURED
- Lint: PASS | FAIL | NOT CONFIGURED
- Tests: PASS | FAIL | NOT CONFIGURED (X passed, Y failed)
## Decisions Made
[bullets, or "None"]
## Risks
[fragile or incomplete bits]
## Next Steps
1. [actionable]
2. [actionable]
## Next Recommended Command
[exact slash command, e.g. `/onboard deep finish auth`]
## Key Files
- [files next session should read first]
3. Append to decisions.md (only if real decisions were made)
Append new entries — never overwrite. Skip trivial choices (naming, formatting). Log choices that would be re-litigated without context: tech picks, architecture, pattern decisions, scope cuts. Skip if a matching title already exists.
Format:
## [date]: [title]
**Choice:** …
**Why:** …
**Context:** …
4. Append to gotchas.md (only if mistakes happened)
Numbered rule per mistake. Skip if none.
5. Append metrics line
echo '{"date":"YYYY-MM-DD","files_touched":N,"verification_runs":N,"gotchas_added":N,"signals_captured":N,"decisions_logged":N}' >> .claude/metrics.jsonl
Counts (deterministic — don't guess from memory):
files_touched:git diff --name-only | wc -lsignals_captured:grep -c "$(date -u +%Y-%m-%d)" .claude/signals.jsonl 2>/dev/null || echo 0- Others: count what you actually added this session.
6. Report
One paragraph: what shipped, uncommitted changes, failing checks. No epic summary — the user will read primer.md.
$ARGUMENTS
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 · 86 lines · 13 tokens per session scan B 00a2544a0870
wrap-up is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 542 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
_subagent-discovery
Whenever a command needs to pick a subagent for a task (planning, task generation, or implementation execution). Do not hardcode agent names in command templates. Do not assume a specific agent exists.
instinct-import
Import instincts from external sources.
evolve
Analyze instincts and suggest or generate evolved structures.
model-config
View or change the primary model that handles your coding work across srooter (the gateway), the route-task hooks, and Maggy. One setting, read everywhere. Stored in /.claude/model-config.json.
ask
Consult a craft agent. Routes your question to the best mind in the workshop - not a menu, a recommendation.
plan
Execute the implementation planning workflow using the plan template to generate design artifacts.