Borrowing it
Nothing to install: this file belongs to design-and-deliver/claude-code-autoconfig. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/design-and-deliver/claude-code-autoconfig/main/.claude/commands/create-wip-report.mdgit clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfigWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/create-wip-report)<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/create-wip-report"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/create-wip-report/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/create-wip-report"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/create-wip-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.08614 |
| Opus 5.5 | $0.00000 | $0.03446 |
| Sonnet 5.5 | $0.00000 | $0.01723 |
| Haiku 4.5 | $0.00000 | $0.00861 |
Grade B, and why
create-wip-report 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 2mo 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.
`## Ledger`. Read the Ledger tail and the substep list, never the whole doc. `.claude/plans/` is How it starts
The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create-wip-report
Half a dozen sessions run against this repo at once and every one of them holds state that exists
nowhere but its own context window. /fleet says who is live and what sits unlanded in a worktree;
/plan-progress says how far a plan doc got. Neither says what each session is actually trying to
accomplish, how far it got, and what would break if it died right now. That is what a WIP note is.
Write them at a natural pause — before a batch of /clears, before stepping away, before a merge
train. They are a snapshot, not a log: cheap to regenerate, never edited in place.
A finished session's note is different, and Step 5 treats it differently. A live note answers
"where is this now?" — a question that expires the moment the work lands. What survives is why the
work happened and what it taught, so a done session is re-rendered into the tracked
reports/wip/done/ archive with the expiring parts dropped and a Lesson added.
It writes only inside reports/wip/, and never commits. It does not merge, commit, reap a
worktree, run the hook-fleet actuator, edit CLAUDE.md, or touch another session's files. Where it
has a finding — including a lesson worth promoting into CLAUDE.md's ## Discoveries — it proposes
it in the report and leaves the decision to the user.
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.
- 2mo ago First seen · 565 lines · 0 tokens per session scan B e76264c00921
create-wip-report is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,614 tokens. 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
init-project
Initialize project with CLAUDE.md template - adaptive detection for new or existing projects.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
update-docs
Scan recently modified files and update the matching documentation.
handoff
Write a session handoff document for continuity.
optimize
Run the credo optimisation audit for the current repo: a freshness check, then a read-only scan (conflict hotspots, changelog fragments, test-stage convention, dogma settings, parallelism readiness, and - only if the user says Yes when asked before the scan - instruction consistency across the global and repo…
gws-tasks
List, create, complete, and manage Google Tasks.