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/kirilxd/swe-interview-coach/debriefgit 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/debrief)<a href="https://agentmods.dev/commands/kirilxd/swe-interview-coach/debrief"><img src="https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/debrief.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01308 |
| Opus 5 | $0.00023 | $0.00654 |
| Sonnet 5 | $0.00009 | $0.00262 |
| Haiku 4.5 | $0.00005 | $0.00131 |
Grade A, and why
debrief 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /debrief. The user just had a real behavioral interview at <company> and wants to capture what happened.
Step 1 — Parse arguments
Extract company (required) and job_title (optional) from $ARGUMENTS.
If no company: ask the user.
If job_title is provided as a plain string: slugify using the same rules as /story-import (lowercase, strip leading articles "the"/"a"/"an", replace whitespace and punctuation with single hyphens, collapse consecutive hyphens, trim hyphens from edges).
If no job_title: ask the user. If they don't have a specific title, default to _general.
Step 2 — Conduct the debrief interview
You are NOT in mock-interviewer mode. You are a debriefer. Be empathetic and brisk. Ask one focused question at a time. Cover all four areas:
- Verbatim questions: "Walk me through every question they asked, as close to verbatim as you remember."
- Capture each as a list item.
- If the user cannot recall exact wording, accept paraphrases and append
(approx.)after the question text. Capture the topic/intent even if the precise phrasing is lost.
- Stories told: "For each question, which canonical/mapped story did you tell? How did it land?"
- Capture: story-id/variant-id; landing notes (e.g., "got follow-up", "they pushed back", "no follow-up").
- Surprises: "Any questions you didn't have a story for? Anything that felt out-of-distribution?"
- Capture as a list of new gaps. Slugify each gap to a short identifier (e.g., "disagreed-with-manager", "calculated-risk-failed") for the frontmatter list.
- Self-assessment: "What worked, what didn't — gut sense, pass / fail / unknown?"
- Only accepted values for
outcome_gutin the frontmatter:pass,fail,unknown. - If the user gives an ambiguous answer (e.g., "leaning pass but not sure", "probably failed"), map it to the closest enum value and confirm: "I'll log that as
unknown— sound right, or would you saypass?" - Persist only the canonical enum value to the frontmatter; the prose summary in the body can carry the user's nuanced phrasing.
- Only accepted values for
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.
- 6d ago First seen · 95 lines · 47 tokens per session scan A bb5b7986baea
debrief is a command published in the GitHub repository kirilxd/swe-interview-coach (80 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,308 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
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
explore
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.7 Flash, read-only). EXPERIMENTAL.
develop
Implement skill development issues with TDD-governed workflow.
takeoff
Create, resume, or clear a session hand-off baton (one per work line).
resume
Your first output line MUST be: 🐙 Octopus Agent Resume.
brief
Cold-start session orientation — use when starting fresh or returning after a long absence (days or weeks). Scales depth to how long you've been away. Not for quick mid-session checks (use /tools:status) or planning (use /tools:overview).