agentmods.dev

code-specialist

code-specialist is a skill for Claude Code, Codex from benchflow-ai/benchflow. It costs 33 tokens per session (174 once invoked), scanned A, original, Apache-2.0.

A specialist delegation guide for difficult coding work. It describes when to hand a problem to another model, such as for algorithms, performance tuning, complex debugging, or exact code generation.

In plain words
What is it for?
Use it for graph or dynamic-programming algorithms, improving slow code, investigating race conditions or memory issues, and generating precise regular expressions, SQL, or shell commands.
Why use it?
It helps structure technical requests so the specialist has the required behavior, constraints, language, and edge cases before producing code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 363repo +4 yesterday A scan SkillSpector: pass 33 tokens original Apache-2.0

Good fit Use it for graph or dynamic-programming algorithms, improving slow code, investigating race conditions or memory issues, and generating precise regular expressions, SQL, or shell commands.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/benchflow-ai/benchflow/models-as-skills
View source ↗ benchflow-ai/benchflow benchflow.ai
Install

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.

Any agent
npx skills add benchflow-ai/benchflow --skill models-as-skills
Clone the repo
git clone --depth 1 https://github.com/benchflow-ai/benchflow

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 code-specialist

README.md
[![agentmods](https://agentmods.dev/badge/skills/benchflow-ai/benchflow/models-as-skills/github.svg)](https://agentmods.dev/skills/benchflow-ai/benchflow/models-as-skills)
Your own site
<a href="https://agentmods.dev/skills/benchflow-ai/benchflow/models-as-skills"><img src="https://agentmods.dev/badge/skills/benchflow-ai/benchflow/models-as-skills/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 code-specialist

Your own site · 80×15
<a href="https://agentmods.dev/skills/benchflow-ai/benchflow/models-as-skills"><img src="https://agentmods.dev/badge/skills/benchflow-ai/benchflow/models-as-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 174 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 pass 7 Sept 2026
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 $0.00033 $0.00174
Opus 5.5 $0.00013 $0.00070
Sonnet 5.5 $0.00007 $0.00035
Haiku 4.5 $0.00003 $0.00017

Measured 2mo ago against content hash 3ef119603223, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-specialist 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

benchmarks/models-as-skills/SKILL.md · 25 lines

What it actually says

Code Specialist

When facing a complex coding task, delegate to the specialist rather than solving it yourself.

When to delegate

  • Algorithm implementation requiring specific knowledge (graph algorithms, dynamic programming)
  • Performance optimization (O(n²) → O(n log n) conversions)
  • Debugging complex race conditions or memory issues
  • Code generation requiring precise syntax (regex, SQL, shell)

How to use

Describe the problem clearly to the specialist. Include:

  1. What the code should do (input → output)
  2. Constraints (time/space complexity, language)
  3. Edge cases to handle

The specialist returns code that you should integrate into your solution.

Files

What ships with it

2 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.

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. 2mo ago First seen · 25 lines · 33 tokens per session scan A 3ef119603223

Subscribe to this mod's changes

code-specialist is a skill published in the GitHub repository benchflow-ai/benchflow (363 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 174 once invoked, about $0.0001 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.

Building agentsbenchmarkevals
Related

code-specialist compared with skills from other repositories

code-specialist next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
code-specialistbenchflow-ai/benchflowSkill363yesterdayApache-2.0A33Claude Code, Codex
lastlight-evalsnearform/lastlightSkill45yesterdayMITA185Claude Code
stetStet-AI/stet-cliSkill519d agononeA116Claude Code, Codex
maven-plugin-configurationbenchflow-ai/skillsbenchSkill1.9k5d agoApache-2.0A31Claude Code, Codex
erlang-otp-behaviorsbenchflow-ai/skillsbenchSkill1.9k5d agoApache-2.0A52Claude Code, Codex
openai-visionbenchflow-ai/skillsbenchSkill1.9k5d agoApache-2.0A17Claude Code, Codex
powerliftingbenchflow-ai/skillsbenchSkill1.9k5d agoApache-2.0A21Claude Code, Codex