Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add archugunov/pm-job-search/plugin install pm-job-searchWrote 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/skills/archugunov/pm-job-search/interview-analysis)<a href="https://agentmods.dev/skills/archugunov/pm-job-search/interview-analysis"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/interview-analysis/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/skills/archugunov/pm-job-search/interview-analysis"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/interview-analysis.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 | $0.00176 | $0.03229 |
| Opus 5 | $0.00088 | $0.01614 |
| Sonnet 5 | $0.00035 | $0.00646 |
| Haiku 4.5 | $0.00018 | $0.00323 |
Grade A, and why
interview-analysis 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 12d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/interview-analysis — post-interview debrief from a transcript
Single-pass analysis. Take a transcript (or notes), produce a debrief that's useful for: (a) the next round at the same company, (b) updates to the user's universal artefacts (stories, anti-patterns), (c) status decisions on meta.md.
Voice: the transcript-source prompt, stage prompt, and the written debrief itself follow ${CLAUDE_PLUGIN_ROOT}/TONE.md. Apply the low-effort-first principle — accept notes if no transcript is available, infer Company / stage from filename if possible, only ask when the answer can't be derived.
Inputs
- Transcript source — resolve in this priority order. The FIRST source that produces content wins:
- Pasted content in the same message as the invocation.
--from-file <path>— read from the given path (can be inside or outside the workspace).- Auto-Granola fetch — if
userdata/integrations.mdshowsgranolastatuswiredAND neither of the above produced content, automatically attempt the Granola fetch (see "Granola fetch" below). No flag needed. - Prompt the user —
Paste the transcript, or give me a file path.Only fires when 1-3 all came up empty.
- If the user has only notes (not a verbatim transcript), accept them — flag in the debrief that analysis is from notes, not transcript.
<Company>— required. Take as positional arg (/interview-analysis Plaid), infer from--from-fileparent folder if path is insideuserdata/companies/<Co>/, or ask if neither.<stage>— required for the filename and for shaping. Pass via--stageor ask:Which round was this — recruiter / hiring-manager / panel / cpo-round / final-loop / take-home / other?Free-text accepted; will be slugged.userdata/integrations.mdif it exists — parse the## granolasection for wired-status. Skip silently if absent.userdata/companies/<Co>/meta.mdandresearch-brief.md— for company context.- The most recent
userdata/companies/<Co>/interview-prep-*.mdif it exists — for the "vs the prep" delta analysis. Match on--stageif multiple; otherwise pick the most recent same-stage prep, or the most recent prep regardless. userdata/profile.md—## Positioning,## Tone of Voice,## What NOT to Frame As.- All
userdata/stories/*.md— to spot which stories were used (match by title hints in the transcript) and judge whether the angles landed.
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.
- 12d ago First seen · 189 lines · 0 tokens per session scan A adfb90f96ebd
interview-analysis is a skill published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 16d ago), licensed MIT. It adds 176 tokens to every session and 3,229 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
interview
Produce a tailored interview prep sheet (behavioral, technical, system design, company) from a job description and the user's resume.
tutorial
Interactive walkthrough for new users. Learn by doing — each step creates real content in your vault. Three tracks (researcher, manager, personal) with a universal learning arc. Triggers on "/tutorial", "walk me through", "how do I use this".
learn
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".
course-builder
Use whenever the user wants to ingest a new course's materials (lecture notes, textbook chapters, HW problems, HW solutions) and build the course-specific knowledge base — patterns.md (recurring solution techniques), coverage.md (HW-to-section map with 🔥 exam tiers + ⚠weak flags), and summary.md (topic tree). Invoked…
alt-import
Parse an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam-probability signal into the PAIDEIA course index — write course-index/radar.md, annotate course-index/coverage.md with a lecture-emphasis column and divergence flags, and seed a gold-zone weakmap. Invoked by /paideia:alt. The export…
mock-interview
Mock interviewer — role-plays a hiring-bar interviewer for an interactive mock interview, asking one question at a time, drilling deeper adaptively, scoring in real time, and identifying weak spots. Company styles are loaded from your configurable company-style library.