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.
git clone --depth 1 https://github.com/kirilxd/swe-interview-coachWrote 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/kirilxd/swe-interview-coach/story-rehearse)<a href="https://agentmods.dev/commands/kirilxd/swe-interview-coach/story-rehearse"><img src="https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/story-rehearse/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/kirilxd/swe-interview-coach/story-rehearse"><img src="https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/story-rehearse.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 | $0.00061 | $0.01474 |
| Opus 5 | $0.00030 | $0.00737 |
| Sonnet 5 | $0.00012 | $0.00295 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
story-rehearse 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 11d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /story-rehearse.
Step 1 — Parse arguments
Extract from $ARGUMENTS:
story_id(required, first positional).variant(optional, second positional).company(optional, value of--company).job_title(optional, value of--job-title).
Mode: mapped if --company is set, else canonical.
If story_id is missing: list available IDs by globbing $CLAUDE_PROJECT_DIR/behavioral/stories/*.md and ask the user to pick.
Step 2 — Resolve story file
- Canonical mode:
$CLAUDE_PROJECT_DIR/behavioral/stories/<story_id>.md. - Mapped mode:
$CLAUDE_PROJECT_DIR/<company>/behavioral/mapped-stories/<job_title-or-_general>/<story_id>.md. If--job-titleis omitted in mapped mode, default to_general.
If the file doesn't exist:
- Canonical: list available IDs from
behavioral/stories/*.mdand ask the user to pick. - Mapped: if the mapping directory doesn't exist (or contains no
<id>.mdfiles), prompt the user with a numbered choice:No mapping for <company>/<job_title>. Choose: (1) run /story-map <company> first, (2) cancel.Wait for the user's response (1-2). If (1), complete the equivalent of/story-map <company>before continuing here. If (2), abort with no file writes. If only this story's mapped file is missing (other mappings exist), list available mapped story IDs and ask.
Read the resolved file.
Step 3 — Resolve variant
If variant is empty or not present in the file:
- Canonical: parse the file's
### Variant: <id>headers; show the list to the user as a numbered choice and ask them to pick. - Mapped: parse the
### Q:blocks (each has a**Maps to canonical variant:** <id>line); show the question text + canonical-variant id pairs as a numbered choice and ask the user to pick. - If no
### Variant:headers are found in canonical mode: report to the user that the story has no variants yet, suggest editing the file directly or running/story-addto add them with the extractor's help, then abort. - If no
### Q:blocks are found in mapped mode: similar — suggest running/story-map <company>to (re)generate mapped variants, then abort.
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.
- 11d ago First seen · 113 lines · 61 tokens per session scan A e2c7b5d51402
story-rehearse is a command published in the GitHub repository kirilxd/swe-interview-coach (80 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,474 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 commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
check-dev
Type-check a Z specification with fuzz.