Agent skill · Audited from source
Ralph Specum Design
skill · tzachbon/smart-ralphMIT licenceAudited 18 Oct 2026 · source a73b124937d9
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit a73b124937d9 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 5 findings, 0 critical or high. What it does: This skill should be used only when the user explicitly asks to use `$ralph-specum-design`, or explicitly asks Ralph Specum in Codex to run the design phase.
Cite
Cite this page
ModelsAtlas. “Ralph Specum Design (tzachbon/smart-ralph)”. Retrieved 18 Oct 2026. https://modelsatlas.com/skills/tzachbon/ralph-specum-design
Trust audit
Audit 0.4.1 · source read 18 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 16,667 of 17,602 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 5 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (5)
MEDIUMInventory / provenanceinv.symlink · .claude/skills/Command Development
.claude/skills/Command Development
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .claude/skills/Hook Development
.claude/skills/Hook Development
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .claude/skills/MCP Integration
.claude/skills/MCP Integration
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .claude/skills/Plugin Settings
.claude/skills/Plugin Settings
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .claude/skills/Plugin Structure
.claude/skills/Plugin Structure
- Why
- link not followed
- Fix
- —
Audit 0.4.1 · source sha a73b124937d9 · 18 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishertzachbon GitHub userOwner of the repository this skill is read from
- Source foldertzachbon/smart-ralph/plugins/ralph-specum-codex/skills/ralph-specum-designThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdicta73b124937d9A new audit runs when the source changes
- Repository statusNot archivedLast push 32 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: This skill should be used only when the user explicitly asks to use `$ralph-specum-design`, or explicitly asks Ralph Specum in Codex to run the design phase.
--- name: ralph-specum-design description: This skill should be used only when the user explicitly asks to use `$ralph-specum-design`, or explicitly asks Ralph Specum in Codex to run the design phase. metadata: surface: helper action: design --- # Ralph Specum Design You are a **coordinator, not an architect** -- delegate ALL work to an `architect-reviewer` sub-agent. Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory. ## Contract - Resolve the active spec by explicit path, exact name, or `.current-spec` - Require `requirements.md` - Merge state fields only - Keep the Ralph disk contract unchanged ## Action 1. Resolve the active spec. If none exists, stop. 2. Require `requirements.md`. Read `research.md` when present, `.progress.md`, and current state. 3. Run `phase_gate.py mode` through `"$RALPH_CODEX_PLUGIN_ROOT/scripts/phase_gate.py"` with `STATE` and exact `--quick`, exact `--interactive`, or no flag. Reject both, `-q`, variants, and natural-language substitutes. 4. In interactive mode, require artifact approval for the current `requirements.md` before starting design. Exact quick mode continues with the validated artifact. 5. Run prototype record selection with the resolved `basePath` before generation: ```bash python3 "$RALPH_CODEX_PLUGIN_ROOT/scripts/prototype_records.py" select-downstream --base-path "$BASE_PATH" --state "$BASE_PATH/.ralph-state.json" ``` 6. Include only affected, valid, `gateApproved: true`, non-superseded records returned by the selector. Exclude malformed, superseded, skipped, failed, inconclusive, cancelled, and normal-mode excluded records. 7. Stop before generation when selection reports an `activePrototypes` blocker for design. Name the active ID and route resume through `$ralph-specum-prototype`. 8. Stop when selection reports stale requirements, research, design, or task indexes that affect design. Route to the earliest stale phase. Allow proven unrelated work only when the selector reports no dependency on the active prototype, stale artifact, stale task index, or approved transfer path. 9. Clear any prior approval gate by merging `awaitingApproval: false` before generation. 10. When `research.md` exists, require skill discovery pass 2 against the goal plus final research. When it is absent, require pass 1 against the goal alone. Run the applicable pass when the state lacks its revision. Select explicitly named skills and record harness-shadowed duplicates. 11. Load `"$RALPH_CODEX_PLUGIN_ROOT/skills/interview-framework-codex/SKILL.md"`, its required algorithm and domain-modeling references, and all selected domain contracts in both interactive and quick mode. In interactive mode, use its focused brainstorming method for material architecture choices, stable interfaces, compatibility or migration decisions, and operational risk. Inspect repository facts and existing conventions instead of asking. 12. In interactive mode, require explicit `approve and delegate`; in exact quick mode, record `bypassed_quick`. In both modes, run `phase_gate.py check-delegation` with the current loaded-manifest identity before creating the child. Apply the shared hard-transition invariant before design writer dispatch. A failed `check-delegation` in either mode ends this invocation before phase transition, child dispatch, or target-artifact write; after a normal-mode failure, the next explicit invocation creates a fresh manifest/interview identity and does not create an alternate quick bypass. 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. 13. **Delegate** design generation to an `architect-reviewer` sub-agent. Pass the absolute helper path, state path, identity tuple, unique teammate dispatch identity, verbatim manifest, requirements, research, selected prototype evidence, the clean blocker/stale-gate result, and interview context. The child reloads and records the manifest, passes `check-agent-write` with that unique identity, and writes `design.md`. Do NOT write design.md yourself. 14. Read the sub-agent's output and validate it exists. 15. Merge state with `phase: "design"` and `awaitingApproval: true` (or `false` when exact `--quick` is active). 16. Update `.progress.md` with design decisions, open risks, integration contracts, skill discovery, and next step. 17. If spec commits are enabled, commit only the spec artifacts. ### Stop Behavior - **Without `--quick`**: STOP HERE. Display the walkthrough summary and approval prompt. Do NOT continue to tasks. Wait for the user to explicitly approve and request the next phase. - **With exact `--quick`**: Record the quick bypass and continue directly into tasks. ## Output Shape The result should cover architecture, interfaces, data flow, file changes, technical decisions, error handling, and test strategy. ## Response Handoff - After writing `design.md`, name `design.md` and summarize the design briefly. - When normalized `quickMode` is false, end with exactly one explicit choice prompt: - `approve current artifact` - `request changes` - `continue to tasks` - Treat `continue to tasks` as approval of `design.md`. - With exact `--quick`, do not show this prompt; continue directly to tasks after the gates succeed. - During artifact review, `apply the changes` immediately delegates already-recorded feedback through a new unique dispatch, redisplays the artifact, and stays at this approval gate. Ask one focused change question only when no feedback is pending. Control-only `continue`, `proceed`, and `go ahead` approve nothing.
Excerpt, first 5,916 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit a73b124
git clone https://github.com/tzachbon/smart-ralph git -C smart-ralph checkout a73b124937d9
The author documents no install command, so this uses the repository directly. Our verdict covers commit a73b124937d9 only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Codex | Mentioned in its text, not tested | Skills for Codex · About Codex |
Audit history
Every audit, every source change
- !CAUTION B 89 / 100
first audit · source
a73b124937d9
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/tzachbon/ralph-specum-design/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
All coding & review skills →tzachbon/smart-ralph
Use only when the user explicitly invokes `$ralph-specum`, requests Ralph Specum in Codex, or asks Ralph Specum to handle a named phase or optional prototype.
tzachbon/smart-ralph
This skill should be used only when the user explicitly asks to use `$ralph-specum-cancel`, or explicitly asks Ralph Specum in Codex to stop execution or remove a spec.
tzachbon/smart-ralph
This skill should be used only when the user explicitly asks to use `$ralph-specum-feedback`, or explicitly asks Ralph Specum in Codex to draft or submit feedback.
tzachbon/smart-ralph
This skill should be used only when the user explicitly asks to use `$ralph-specum-help`, or explicitly asks Ralph Specum in Codex for help or command guidance.
tzachbon/smart-ralph
This skill should be used only when the user explicitly asks to use `$ralph-specum-implement`, or explicitly asks Ralph Specum in Codex to run implementation for approved tasks, quick mode, or an explicit continue…
tzachbon/smart-ralph
This skill should be used only when the user explicitly asks to use `$ralph-specum-index`, or explicitly asks Ralph Specum in Codex to generate or refresh index artifacts.
Add this badge to your README
[](https://modelsatlas.com/skills/tzachbon/ralph-specum-design/)
<a href="https://modelsatlas.com/skills/tzachbon/ralph-specum-design/"><img src="https://modelsatlas.com/skills/tzachbon/ralph-specum-design/badge.svg" alt="ModelsAtlas: CAUTION B"></a>
Questions about Ralph Specum Design
What does the Ralph Specum Design skill do?
Is Ralph Specum Design safe to install?
What can Ralph Specum Design access on my machine?
What do I need installed to use Ralph Specum Design?
Which assistants does Ralph Specum Design work with?
How current is this page?
Sources
- github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum-c — the audited source at commit a73b124937d9 and every finding aboveObserved · 18 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Ralph Specum Design skill do?
- Is Ralph Specum Design safe to install?
- What can Ralph Specum Design access on my machine?