agentmods.dev

sanad-agent: Skill for Claude Code

.agents/skills/sanad-subagent-developer/SKILL.md

Sanad Subagent Developer is a skill for Claude Code, Codex from EastStarAI/sanad-agent. It costs 27 tokens per session (728 once invoked), scanned A, original, MIT.

A procedure for a focused Sanad coding task carried out in an isolated Git worktree, a separate working copy of the repository. It covers reading the task plan, making targeted changes, and proving the result.

In plain words
What is it for?
Use it to implement one planned Sanad task, run the required checks, control the isolated runtime with sanad-dev, and return a reviewable result.
Why use it?
It keeps a subagent's work separate from another active runtime and makes the completed change easier to review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is EastStarAI/sanad-agent's own configuration. It tells Claude Code and Codex how to work on sanad-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sanad-agent configures →

not rated 42repo +7 today A scan SkillSpector: warn 27 tokens original MIT
View source ↗ EastStarAI/sanad-agent sanad.eaststarai.com
Reuse

Borrowing it

Nothing to install: this file belongs to EastStarAI/sanad-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/EastStarAI/sanad-agent/main/.agents/skills/sanad-subagent-developer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/EastStarAI/sanad-agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Sanad Subagent Developer

README.md
[![agentmods](https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-subagent-developer/github.svg)](https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-subagent-developer)
Your own site
<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-subagent-developer"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-subagent-developer/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.

agentmods 80×15 button for Sanad Subagent Developer

Your own site · 80×15
<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-subagent-developer"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-subagent-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 728 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, 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 Agent Snooping · line 13
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 37
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00728
Opus 5 $0.00014 $0.00364
Sonnet 5 $0.00005 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 10d ago against content hash 457a0791cf92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Sanad Subagent Developer 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 10d 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.

.agents/skills/sanad-subagent-developer/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sanad Subagent Developer Protocol

Execute one well-defined task in an isolated worktree, prove its Definition of Done, and return a reviewable result without contaminating another active runtime.

1. Read the Plan and Create Isolation

  1. Read the assigned task plan from docs/plans/tasks/<task_id>-<task_name>.md.

  2. Load .agents/skills/sanad-agentic-developer/SKILL.md and follow its isolated-worktree mode.

  3. Create and enter the dedicated worktree before editing, testing, or launching processes:

    git worktree add .agent/worktrees/<task_id>-<branch_name> <branch_name>

  4. Use sanad-dev from inside that worktree for runtime work. Do not offset ports, set SANAD_STATE_HOME, construct a relative SANAD_HOME, or edit tracked runtime configuration manually. The launcher allocates worktree-specific daemon/VM ports, creates one worktree-scoped SANAD_HOME, isolates client preferences, and selects the matching runtime automatically.

  5. Use direct component commands only when diagnosing sanad-dev itself or one process in isolation.

2. Targeted Coding

  1. Modify only the scope established by the task plan and the nearest owning contracts.
  2. Read every applicable AGENTS.md before editing its directory.
  3. Use FVM for every Flutter/Dart command, keep paths workspace-relative, and preserve established ownership boundaries.
  4. Update the corresponding active page under docs/ in the same task. Update an AGENTS.md only when a durable law, invariant, or ownership boundary changes or becomes stale.
  5. Do not overwrite unrelated dirty work already present in the assigned worktree.

3. Verification

  1. Run the relevant analyzer before completion.
  2. Run focused tests covering the changed behavior and failure/recovery paths.
  3. Run the full fast suite only for broad or shared-surface changes.
  4. Run E2E/integration tests only when mocks cannot validate a real daemon/client, socket, restart, persistent-state, provider, or worktree-runtime boundary.
  5. Use sanad-dev run --driver plus .agents/skills/sanad-client-tester/SKILL.md when live UI verification is required. Local and cloud connections are enabled by default; append --no-cloud for explicit local-only verification.
  6. Preserve command exit status while bounding successful analyzer/test output to the final five lines. Rerun only a failing command without filtering when diagnosis needs full output.
  7. Record exact commands, outcomes, skipped coverage, and unresolved uncertainty.

Read the full file on GitHub · 53 lines

Changes

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.

  1. 10d ago First seen · 53 lines · 27 tokens per session scan A 457a0791cf92

Subscribe to this mod's changes

Sanad Subagent Developer is a skill published in the GitHub repository EastStarAI/sanad-agent (42 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 728 once invoked, about $0.0001 per session on Opus 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.

Git and workflowPlanningai-agentcoding-agentdartdesktopdeveloper-toolsflutter
Related

Other skills, from other repositories

release-changelog-harness

Chooses ecosystem-native release and changelog tooling (Changesets, Melos, release-plz) plus binary distribution (GitHub Release tarballs, install.sh) when the product is an executable. Use for release CI, install.sh, versioning, CHANGELOGs, shipping MCP/CLI without clone, or meta repos that only ship skills via npx…

Arenukvern/mcp_flutter · 84 tokens

gitnexus-cli

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki".

Arenukvern/mcp_flutter · 59 tokens

github

A general GitHub skill for understanding repositories, pull requests, and issues through a connected GitHub account. It helps route work to more specific GitHub workflows when needed.

rojim666/SztuCode · 35 tokens

yeet

Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with gh used only as a fallback where connector coverage is insufficient.

rojim666/SztuCode · 49 tokens

gh-address-comments

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

rojim666/SztuCode · 39 tokens

gitlab

Read and manage GitLab projects, issues, merge requests, and pipelines via the GitLab REST API. Use when the user asks about GitLab projects, issues, MRs, or pipelines.

intentic/intentic · 42 tokens