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-add)<a href="https://agentmods.dev/commands/kirilxd/swe-interview-coach/story-add"><img src="https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/story-add/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-add"><img src="https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/story-add.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 | $0.00049 | $0.00644 |
| Opus 5 | $0.00024 | $0.00322 |
| Sonnet 5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
story-add 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /story-add. The user wants to add a new canonical story to $CLAUDE_PROJECT_DIR/behavioral/stories/.
Step 1 — Resolve mode
If $ARGUMENTS is empty: cold mode.
If $ARGUMENTS ends in .pdf (case-insensitive): CV-grounded mode; resolve the path (handle ~/ and surrounding quotes if any).
If $ARGUMENTS ends in .docx: print exactly this message and stop:
DOCX isn't supported. Convert to PDF and retry — PDF is the more universal résumé format anyway.
If $ARGUMENTS is some other format: ask the user to provide a PDF or run cold mode.
Step 2 — Cold mode
Spawn the behavioral-story-extractor subagent with this context:
Mode: cold. The user wants to add one new STAR story. Begin the extraction interview.
After the subagent returns its draft, jump to Step 4.
Step 3 — CV-grounded mode
Read the PDF using the Read tool. If the read returns very short or empty content (suggesting a scanned-without-OCR PDF or corrupt file), report that and ask the user for an alternative source (paste the text, point at a different file, or fall back to cold mode).
Spawn the behavioral-story-extractor subagent with this context:
Mode: cv-grounded. Here is the user's resume content:
Begin the extraction interview by listing 3-5 candidate experiences and asking the user to pick one.
After the subagent returns its draft, jump to Step 4.
Step 4 — Confirm and write
Show the draft to the user verbatim. Ask: "Look right? Anything to revise before I save?"
If user requests revisions, apply them to the draft. Repeat until user confirms.
On confirmation:
- Compute target path:
$CLAUDE_PROJECT_DIR/behavioral/stories/<id>.md. - If a file already exists at that path, prompt the user with a numbered choice:
A file already exists at behavioral/stories/<id>.md. Choose: (1) overwrite, (2) write as <id>-v2, (3) write as <id>-<YYYY-MM-DD>, (4) cancel.Wait for the user's response (1-4) and act accordingly. - Use the
Writetool with the full absolute target path — it creates any missing intermediate directories automatically. No explicitmkdiris needed.
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 · 58 lines · 49 tokens per session scan A 507bc744d3bc
story-add is a command published in the GitHub repository kirilxd/swe-interview-coach (80 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 644 once invoked, about $0.0002 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
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.
adr-supersede
Create a new ADR that supersedes an existing one.
check-dev
Type-check a Z specification with fuzz.