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/feedbackgit 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/feedback)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/feedback"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/feedback.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 | $0.02155 |
| Opus 5 | $0.00000 | $0.01077 |
| Sonnet 5 | $0.00000 | $0.00431 |
| Haiku 4.5 | $0.00000 | $0.00215 |
Grade A, and why
feedback 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
feedback — Capture Feedback, Outcomes, and Corrections
A lightweight command for capturing information that arrives between structured workflows. Feedback does capture, not analysis. Analysis happens in analyze, progress, and prep when the data becomes relevant.
When to Use
- Recruiter or interviewer sends feedback (formal or informal)
- Candidate learns an interview outcome (advanced, rejected, offer)
- Candidate wants to correct or adjust a previous coaching assessment
- Candidate remembers something from a past interview they want to log
- Candidate has meta-feedback about the coaching itself
Input Type Detection
Classify the candidate's input into one of five types. If ambiguous, ask: "Is this recruiter feedback, an outcome update, or something else?"
Type A: Recruiter/Interviewer Feedback
Trigger: Candidate shares feedback received from a recruiter, interviewer, or hiring manager.
Capture process:
- Record the feedback as close to verbatim as possible. Ask: "Can you share exactly what they said? Even rough wording helps — paraphrasing loses signal." If the candidate's account is vague or thin, use guided extraction prompts: "Did they mention specific skills or experiences? Did they compare you to other candidates? Did they give any process feedback — like timeline, next steps, or what the team thought? Did they say anything about culture fit or team dynamics?" These prompts help candidates recall details they might otherwise skip.
- Identify the source: recruiter, interviewer, or hiring manager.
- Map the feedback to the most relevant scoring dimension(s) — but hold this lightly. Some feedback maps cleanly ("your answers were hard to follow" → Structure), some doesn't ("we went with a candidate with more domain experience" → external factor, not a coaching gap).
- If the feedback contradicts the coach's assessment, note the discrepancy — don't dismiss it. External feedback is higher-signal than internal scoring. This is a drift signal — check whether the contradiction is isolated or part of a pattern. If 2+ pieces of external feedback contradict coach scoring on the same dimension, log it in
coaching_state.md→ Calibration State → Scoring Drift Log and flag for the nextprogresscalibration check.
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 · 144 lines · 0 tokens per session scan A ffd014971150
feedback 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 2,155 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.