code-specialist

A way to hand difficult programming tasks to a specialist model. It is intended for focused help with algorithms, performance, debugging, or code that requires exact syntax.

In plain words
What is it for?
Delegating graph or dynamic-programming algorithms, improving time complexity, debugging race conditions or memory issues, and generating precise regular expressions, SQL, or shell code.
Why use it?
It provides a separate source of focused code expertise when a problem involves complex logic, slow code, hard-to-find bugs, or tricky edge cases.

Skill for Claude CodeCodex

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.

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

Made for: Claude Code, Codex.

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. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00033 $0.00174
Opus 5 $0.00016 $0.00087
Sonnet 5 $0.00007 $0.00035
Haiku 4.5 $0.00003 $0.00017

Measured 2d ago against content hash 3ef119603223, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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

This is a copy

100% identical to code-specialist — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

docs/examples/task-md/generated-skill-eval/models-as-skills/optimize-quadratic-to-nlogn/environment/skills/code-specialist/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

1 file 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. 2d 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 (335 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 174 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to code-specialist, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

lastlight-evals

Scaffold, configure and run a Last Light EVALS workspace — the harness that runs Last Light's real workflows against a mocked GitHub and grades them deterministically. Use when the user wants to "set up / scaffold Last Light Evals", "create an evals workspace or instance", "run evals", "compare models", or author new…

nearform/lastlight · 185 tokens

mobile-principles

Mobile-specific UX principles - touch targets, hover-less doctrine, thumb zones, safe areas, gestures, mobile perf budgets. Cross-platform (web mobile, iOS, Android).

Jwuthri/Tracely-ai · 40 tokens

canvas-generative

Algorithmic and generative art with Canvas 2D - particles, flow fields, noise, fractals, L-systems.

Jwuthri/Tracely-ai · 30 tokens

threejs-r3f

Three.js and React Three Fiber sub-skill - 3D scenes, shaders, postprocessing.

Jwuthri/Tracely-ai · 26 tokens

portfolio

Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…

suyoumo/ClawProBench · 69 tokens

parallel-pr-review

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

suyoumo/ClawProBench · 67 tokens