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/noamseg/interview-coach-skill/decodegit clone --depth 1 https://github.com/noamseg/interview-coach-skillWrote 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/noamseg/interview-coach-skill/decode)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/decode"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/decode.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 | $0.00000 | $0.04270 |
| Opus 5 | $0.00000 | $0.02135 |
| Sonnet 5 | $0.00000 | $0.00854 |
| Haiku 4.5 | $0.00000 | $0.00427 |
Grade A, and why
decode 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 4d 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
decode — JD Analysis + Batch Triage
How JDs Actually Work (Reference Knowledge)
JD Structure Patterns: JDs follow predictable structures — company intro, role summary, responsibilities, requirements, nice-to-haves, benefits. But the signal isn't in the structure, it's in the language.
Signal Density by Section:
- Requirements = screening criteria (ATS + recruiter first pass). What gets you through the door.
- Responsibilities = what the role actually does. Often more honest than requirements.
- Nice-to-haves = the ideal candidate profile. What "Strong Hire" looks like beyond baseline.
- Company intro = culture signals and positioning. How the company wants to be perceived.
- Benefits = comp philosophy signals. Equity-heavy = startup. Benefits-heavy = mature org.
The 6 Decoding Lenses (adapted from prep.md's JD Parsing Guide — decode makes these the main event):
- Repetition frequency — Count how often key themes appear. If "cross-functional collaboration" appears 3 times, it is a primary evaluation criterion. Most repeated = most important, regardless of where it appears.
- Order and emphasis — What's listed first in responsibilities/requirements? First = highest priority. The first 3 bullets typically reflect the top 3 evaluation criteria.
- Required vs. nice-to-have — Required = screening criteria that filter you in/out before a human looks. Nice-to-have = what differentiates "Hire" from "Strong Hire." Many candidates skip nice-to-haves — this is a mistake.
- Verb choices — "Own" vs. "support" vs. "contribute to" signal autonomy and scope. "Own end-to-end" is a fundamentally different job from "contribute to team efforts." "Drive" vs. "execute" signals strategy vs. implementation.
- Between-the-lines signals — Euphemisms decoded. "Fast-paced environment" = likely understaffed or rapid change. "Comfortable with ambiguity" = undefined role or early-stage. "Stakeholder management" = political environment. "Wear many hats" = no clear role boundaries. These are interpretations, not facts — confidence-label accordingly.
- What's missing — Absence is information. A PM JD that doesn't mention data/analytics signals team maturity (or lack of PM influence on data). An engineering JD that doesn't mention testing may indicate culture. A senior role with no mention of mentoring signals an IC-heavy org.
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.
- 4d ago First seen · 320 lines · 0 tokens per session scan A a1fdbb547c02
decode is a command published in the GitHub repository noamseg/interview-coach-skill (2,092 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,270 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.