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/lab94/frenchie-skill/walkthroughgit clone --depth 1 https://github.com/Lab94/frenchie-skillWhat 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 | $0.00000 | $0.00414 |
| Opus 5 | $0.00000 | $0.00207 |
| Sonnet 5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
walkthrough 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 yesterday.
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.
What it actually says
/walkthrough
Walk through the implemented result from the user's perspective.
Check acceptance criteria, important states, copy, data behavior, error cases, and changed workflows. Use screenshots or local browser checks when a UI is involved and the environment supports them.
Alias: /frenchie-walkthrough.
Artifact Contract
/walkthrough must produce or update 07-walkthrough.md in the active feature folder. Walking through and only replying in chat is not enough — /redo cascade and /method-check rely on the artifact being on disk.
Required 07-walkthrough.md sections:
AC Verification
For each AC-NNN from 02-acceptance-criteria.md, record verified / partially verified / unverified with reason. Reference the exact path or interaction that proved it.
States
A state-by-state table covering Default, Loading, Empty, Error, Disabled, and Permission denied — whether each state was triggered and what was observed.
Copy
Microcopy actually rendered: labels, buttons, empty states, errors, success confirmations, tooltips. Flag mismatches against 05-design.md.
Data Behavior
Inputs accepted, inputs rejected, defaults, persistence, optimistic updates, retry semantics, cross-session continuity.
Errors
Error messages that surfaced, recovery paths offered, and whether they map to designed error states.
Changed Workflows
Existing flows the change affected — regressions, broadened scope, removed steps. Note any not called out in the requirement.
Open Issues
Defects, surprises, or follow-ups. Route blockers to /fix-review; route non-blockers to a new requirement or /redo of the upstream stage.
Output Contract
The chat reply should include:
## Walkthrough Summary
## AC Status Snapshot
## Blocking Findings
## Non-blocking Follow-ups
## Recommended Next Command
When a section in the artifact is unknown (e.g. environment did not support browser checks), mark it explicitly rather than silently omitting it.
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.
- yesterday First seen · 56 lines · 0 tokens per session scan A 71f655ba3b52
walkthrough is a command published in the GitHub repository Lab94/frenchie-skill (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 414 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.