Skip to content
Back to skills

Sanad

ASecurity

Entry point for every user request. Ask once per new task for Claude or Codex, recommending the current chat engine. Route bounded work directly and uncertain or sensitive work through the selected engine. All Codex roles use xhigh; preserve verification and publishing approval.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 18, 2026
toolsrustgobashsqlnodegitsecurity

Security analysis

A100/100

Pro scans all 11 files and shows the line behind each finding

Scanned November 18, 2026

npx -y skills add developzone5/sanad --skill sanad --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sanad?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Sanad
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/developzone5-sanad-sanad/badge)](https://www.skillsdirectory.com/skills/developzone5-sanad-sanad)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: sanad
effort: medium
description: Entry point for every user request. Ask once per new task for Claude or Codex, recommending the current chat engine. Route bounded work directly and uncertain or sensitive work through the selected engine. All Codex roles use xhigh; preserve verification and publishing approval.
argument-hint: "<task> [engine=claude|codex] [effort=low|medium|high|xhigh|max]"
---

<!-- Author: Eng. Mohammed Almutairi - Developzone.net -->

# /sanad — the task loop

Every request enters here. Route by intent, then load only what the route needs. Nothing is pushed without the explicit yes.

## Step 0 — Choose engine, then route

For a new actionable task, ask **"Which engine for this task?"** with the current chat engine recommended first (Claude or Codex), then wait for the answer. An explicit engine choice answers it already. Follow [engines.md](reference/engines.md) for selection, saved task state, role assignments and host handoff. Follow-ups, questions and delegated children reuse the task choice. Claude keeps medium routing; **Codex stays xhigh for every role and stage**.

- **Teaching / explanation / lesson status** → read the relevant tracker and code, then answer or give one teaching step, in the CLAUDE.md reply shape. No build, no tests, no panel, no reviewer. Nothing else from this skill loads.
- **Check my work / PR review / a question during a task** → the smallest relevant check (or `ship/reference/pr-review.md` for a PR). Report exactly what it proves and what stays unverified. Not a gate, not permission to publish. The existing task then continues.
- **Implement / fix / continue implementation** (a feature, behavior change, bug fix, migration, refactor with behavior risk; a one-line behavior change is not cosmetic) → first run `node ~/.claude/skills/gate/scripts/sanad-timer.mjs request` once for a new task (its time then starts at the user's request; without it the report marks the start `(estimate)`), then route before edits per [boss-routing.md](reference/boss-routing.md): the size check picks Small, Medium or Big, shown as `▸ size: small | medium | big — reason · places: <n>`; call the selected engine's boss for Big work, or when scope, risk or approach is uncertain. Then invoke the internal `sanad-implementation` skill (xhigh) through the host's native skill mechanism; it reads [reference/loop.md](reference/loop.md) (one page: six rules, three sizes) and [reference/execution.md](reference/execution.md) and runs Steps 1–5: understand and list the places → check the facts → design → build and prove → review → gate and ship brief. Reuse a valid route and completed decisions for an unchanged continuation; ask the same boss to reassess only when new scope, risk or evidence invalidates them.
- **Docs/comment edits, trivial mechanical fixes** (typo, rename, one obvious line) → direct, with proportionate verification.
- **Multi-session feature** → `/spec` first (or update the existing spec); then one milestone at a time. **Already-reviewed PR being cherry-picked or promoted** → [promotion.md](../ship/reference/promotion.md): equivalent changes reuse the original reviews; only conflict edits or changed behavior re-enter the loop.

Route each new request by its intent, not by the project or the previous turn. No route waives security, destructive-action or publishing controls, or an unfinished check. Reading a file or writing an effort label does not change runtime effort; if the host cannot activate the required effort, say so.

## Rules on every route

- **Workflow changes get one attack pass, not the task review (user rules 2026-09-28 and 2026-11-17):** the reviewer round and the boss run on the tasks and bugs the user gives, not on changes to the workflow itself (`~/.claude` skills, hooks, CLAUDE.md, settings, `~/.agents` mirrors, Sanad Codex config/agents). Each changed script or hook gets one independent checker before install: a read-only agent that tries to break it (the new tests run on the base copy, the hole it closes, a false refusal of honest work); its confirmed findings are fixed with a test. Prose-only changes need none. Workflow fixes are batched: every agreed fix first, then one PR, one merge, one update of the other machine. Build them as a release: copy the live files to a scratch candidate plus an untouched base copy, edit the candidate, run its suites (`hooks/tests`, `skills/gate/tests`), then install with `bash ~/.claude/scripts/workflow-install.sh <candidate> <base> <release-name>` (drift guard, then the candidate's own proof end to end on the test machine for every `git config --global sanad.e2eRun "<repo>|<folder>|<test command>"` — a page project and a server project — before any file changes, then backup, suites, `backups/RELEASES.md` line). Use literal paths. Hooks apply on their next run; settings changes need a fresh session.
- **Work on another PC (user rule 2026-10-28):** before the first command that runs on another machine (Orca `--environment`, SSH), read [remote-host.md](reference/remote-host.md). Start remote agents and wait for their reports only through its two scripts; never hand-type a launch or a wait.
- **A bug the user reports in shipped or PR'd work** is reproduced in a failing test first, then fixed through the loop, on every path its places list names; the escaped-bug count on that task's line in `memory/task-metrics.md` goes up by one. No bug list is kept or read: the loop works from the change itself.
- **Project incident records stay in the project.** A teammate or post-PR finding becomes a check in THAT project (its tests, lint, rules file), never a line in this file, the global CLAUDE.md or a reviewer prompt; global text stays stack-neutral. Expert instruction gaps are fixed after the PR is open through [expert-learning.md](../braintrust/reference/expert-learning.md).
- **A cycle, not a script.** Red gate → rebuild; invalidated decision → re-convene; every loop-back stated in one line. **Skips are stated, never silent.** **User steering** is answered at once; separate work is queued explicitly. **The ship ask is the hard stop** — no stage, effort or mode removes it.

## Reporting contract — how the loop talks

- **Plain words in chat (user rule 2026-10-22).** Every line the user sees follows CLAUDE.md "How you talk" (Codex: `~/.codex/AGENTS.md`). The user must understand each line without asking. Internal names (route, facts, boss, braintrust, Pass A/B, Done means, gate) stay in files, records and agent prompts; the chat uses the plain shapes below.
- One line per stage, as it happens, in a self-explaining shape:
  - Size of the job (route `direct` / `review` / `braintrust`): `▸ size: text only | small | medium | big, experts plan first — <reason> · places: <n>`
  - Facts checked before building: `▸ checked: <n> facts confirmed, <m> not sure yet`
  - PR plan before building (loop.md Step 1; Medium and Big): `▸ PRs: <n> — <reason>`, then one short line per PR (order, tickets, what it holds, size, base), then the ask for an OK. Small says `1 PR` on its size line and goes on.
  - Build: `▸ built: <n> files changed, <n> tests pass`
  - On every size, one step line each, in this order, so a skipped step shows at once: `▸ places` (the list, every place closed) → `▸ tests` → `▸ fix` → `▸ checks before the proof` (`pre-review --before-proof`) → `▸ red` (the proof run) → `▸ review started` → `▸ checks` (`pre-review`) → `▸ suite` (remote machine first; Small with a slow suite says "left to CI") → the review and gate lines. A step that does not apply says so in its line.
- **A question to the user about a ticket quotes the ticket line that leaves it open (user rule 2026-11-06).** A reviewer's or helper's product question is answered from the ticket's own Expected, Requirements and Acceptance lines first; only a question no ticket line answers goes to the user, with that line quoted. (A "what does QA want" question went to the user although the ticket's Expected line answered it.)
- Review and gate keep their machine lines (`REVIEW:` / `GATE:`, read by the hooks), never a `▸` line. Put one plain sentence on the line before each, e.g. `🟢 A second AI checked the change and found no problems.` A reviewer note is answered by its own machine line, `NOTE <n>: fixed — <what changed and its test>` or `NOTE <n>: user — "<the user's exact words>"`, written in words the user understands. Notes that need the user's decision are asked together, one short line each, with a recommended answer.
- **Running list for multi-item work (user rule 2026-10-26).** When the task has 3 or more items (review comments, bugs, acceptance steps), keep one numbered list in the user's words, each line marked 🟢 done · 🟡 working on it · 🔵 not started · 🔴 blocked. Show it when work starts, again after each item finishes or changes state, and whenever the user asks for status — the user never has to ask "where is the list". Same numbers throughout; new items join at the end.
- Zero prose between stages. No "now I will…", no restating the task.
- Braintrust result to the user: the 6-line "What the user reads" block only; the full record goes to the spec.
- The final message is the ship brief ONLY, in `/ship`'s format (What I changed and why / How I checked it / Risk / Not done / Where it goes, one line each), then the ask. Under 12 lines.
- Detail is pull, not push: keep the evidence (SQL, test output, sweeps) ready and give it only when asked.

Files in this skill

  • SKILL.md9.4 KB
  • reference/backend-scaling.md6 KB
  • reference/boss-routing.md8.1 KB
  • reference/engineering-bar.md10.2 KB
  • reference/engines.md7.1 KB
  • reference/execution.md12.4 KB
  • reference/full-pr-review.md4.7 KB
  • reference/loop-rare-cases.md19 KB
  • reference/loop.md13.7 KB
  • reference/remote-host.md11.7 KB
  • reference/review-checklist.md9.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.