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 skills add tzachbon/smart-ralph --skill interview-framework-codexgit clone --depth 1 https://github.com/tzachbon/smart-ralphWrote 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/tzachbon/smart-ralph/interview-framework-codex)<a href="https://agentmods.dev/skills/tzachbon/smart-ralph/interview-framework-codex"><img src="https://agentmods.dev/badge/skills/tzachbon/smart-ralph/interview-framework-codex/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/tzachbon/smart-ralph/interview-framework-codex"><img src="https://agentmods.dev/badge/skills/tzachbon/smart-ralph/interview-framework-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 30 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00045 | $0.00856 |
| Opus 5.5 | $0.00018 | $0.00342 |
| Sonnet 5.5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
interview-framework-codex 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 1mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex interview framework
Run every normal-mode start, triage, research, requirements, design, and tasks phase through references/algorithm.md and references/domain-modeling.md.
Completion criterion
Delegate only after all of these conditions hold for one identity tuple:
phase,interviewId,discoveryRevision, andcontextDigestmatch in state and in the delegation packet.- The selected skill manifest has status
completeorpartial_warned. - The phase interview has status
completeorskippedafter explicit final approval. phase_gate.py check-delegationsucceeds.
Hard-transition invariant
Run the current check-delegation immediately before each affected phase transition or child dispatch. A failed check-delegation in either mode stops this invocation before state transition, child dispatch, or target-artifact write. After a normal-mode failure, the next explicit invocation uses a fresh manifest/interview identity. After an exact --quick delegation failure, the next explicit invocation reruns discovery, records a fresh phaseSkillLoad and interview identity, and does not reuse a terminal bypassed_quick interview or its discovery revision. Only a matching in-progress collecting or awaiting_confirmation interview is resumable. A matching in-progress interview that has not reached a failed delegation boundary remains valid for resume.
Exact --quick preserves discovery, manifest, parent-delegation provenance, check-delegation, receipt recording, and check-agent-write. Quick mode bypasses interview questions only. Exact --quick separately bypasses final approval. It still runs check-delegation immediately before dispatch, uses the same identity tuple, requires a current complete or partial_warned manifest plus an interview receipt with status bypassed_quick and quickAuthorization.source: "--quick", and has no other bypass.
Hard boundaries
- Ask only critical user decisions that can change phase scope, externally visible behavior, acceptance, architecture, sequencing, or material risk.
- Inspect code, configuration, state, prior artifacts, and selected skill contracts for facts. Do not ask the user for discoverable facts or setup and administration choices.
- Ask the whole currently unblocked critical frontier. Split a frontier only when Codex's native user-input tool limit requires another batch. The current limit is three questions per call.
- Put the recommended option first and state its tradeoff. Offer only viable alternatives.
- Persist each partial answer before asking the next frontier.
- Treat control-only replies such as
apply the changes,continue,proceed, andgo aheadas no answer to an active interview question. - Treat bare
skipduring an active question as an instruction to finish the remaining interview with stated defaults and assumptions. Present the final approval gate before delegation. - Delegate in the same turn after the user explicitly chooses
approve and delegate. - During artifact review, treat
apply the changesas a revision request. Delegate the revision and remain at the artifact approval gate. - Apply domain-language modeling during the grill. Challenge conflicting or vague terms, use concrete boundary scenarios, and record resolved domain terms without creating an ADR.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +4 lines 4313be701229
- 1mo ago First seen · 41 lines · 45 tokens per session scan A 7683dda900c1
interview-framework-codex is a skill published in the GitHub repository tzachbon/smart-ralph (559 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 856 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
blueprint-cloudflare-scaffold
Lay out a Worker with D1 and static Vue assets, with tests that run inside the Workers runtime.
self-assessment
Interactive skill assessment with personalized learning path generation.
project-design
Roteador de processos de design e marca que carrega orientações para criar arquivos DESIGN.md completos para um projeto e suas aplicações de interface.
loom-usage
Meta-orchestration skill for Claude driving loom itself.
loom-c
C language expertise (C11/C17/C23) for memory-safe, portable, production-quality systems code.