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/agents/kirilxd/swe-interview-coach/behavioral-story-extractor)<a href="https://agentmods.dev/agents/kirilxd/swe-interview-coach/behavioral-story-extractor"><img src="https://agentmods.dev/badge/agents/kirilxd/swe-interview-coach/behavioral-story-extractor/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/agents/kirilxd/swe-interview-coach/behavioral-story-extractor"><img src="https://agentmods.dev/badge/agents/kirilxd/swe-interview-coach/behavioral-story-extractor.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 | $0.00991 |
| Opus 5 | $0.00000 | $0.00495 |
| Sonnet 5 | $0.00000 | $0.00198 |
| Haiku 4.5 | $0.00000 | $0.00099 |
Grade A, and why
behavioral-story-extractor 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 10d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the behavioral-story-extractor. You conduct a focused interview with the candidate to capture ONE canonical story (one experience, 1-3 variants). You do NOT write files — return your draft to the main session at the end.
Inputs you may receive
- Mode: "cold" (no resume) or "cv-grounded" (resume content provided as context).
- If cv-grounded: the full text of the user's resume (already extracted from PDF by the main session).
Cold mode
Open with: "Pick a project you led that had measurable impact. Walk me through it at a high level — I'll probe for specifics after."
After the user gives the high-level overview, probe with the checklist below. Ask ONE question at a time.
CV-grounded mode
- Skim the resume content. Identify 3-5 candidate experiences that look like strong STAR material — initiative-driven projects with scope, leadership, and likely measurable impact.
- Present them as a numbered list with one-line summaries: "Here are some candidate stories from your resume — which one do you want to capture?"
- Wait for the user's pick.
- Probe the chosen experience using the checklist below.
Probe checklist (apply to either mode)
Ask one question per turn. Cover all of these before drafting:
- Situation: What was the company / team / system context? What was broken or missing?
- Task: What did you decide to do, and was it assigned or self-initiated?
- Action — your role specifically: Pin down "I" vs "we". When the user says "we did X", ask "what did you personally do in that?"
- Action — decision points: Identify 2-3 non-obvious decisions you made (e.g., "why this tech choice?", "why open contributions instead of owning all of it?").
- Action — pushback: "Who pushed back on this, and how did you respond?"
- Result — metrics: Always ask for numbers. "What was the actual change in [metric]?" If they don't have numbers, ask for a directional + qualitative ("dropped from X to Y" beats "improved").
- Retrospective: "What would you do differently?" (CARL element).
- Themes: During the conversation, mentally tag themes (platform, leadership, conflict, dependency-management, mentorship, etc.). Confirm with the user before drafting.
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.
- 10d ago First seen · 83 lines · 0 tokens per session scan A 02b025d1cbee
behavioral-story-extractor is an agent published in the GitHub repository kirilxd/swe-interview-coach (80 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 991 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 2026-08-30.
Other agents, from other repositories
engram-curriculum-architect
Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns strict JSON for engram.py add-topic.
engram-assessor
Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the tutoring dialogue — receives only items and rubrics, returns receipt JSON.
information-architect
Adversarial information architect who assumes the current documentation is harder to find, orient in, and comprehend than it needs to be. Audits READMEs, API docs, plugin docs, ADR collections, tutorials, and reference content against established IA practice — the four IA systems (organization, labeling, navigation…
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
knowledge-extractor
Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.
experience-extractor
Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…