agentic-engineering

agentic-engineering is a skill for Claude Code from shennawardana23/skillme. It costs 91 tokens per session (1,446 once invoked), scanned A, original, Apache-2.0.

A method for handing one implementation task to an AI coding agent with clear goals, limits, and checks. It treats the human as responsible for defining what done means and reviewing the result.

In plain words
What is it for?
Use it to split work into small, independently checkable tasks, choose an appropriate model tier, and define tests or manual checks for the result.
Why use it?
It reduces vague requests, oversized tasks, and unclear reviews. The agent gets concrete success and regression checks before it starts coding.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skillme plugin — 137 skills, 2 commands shipped together

Good fit Use it to split work into small, independently checkable tasks, choose an appropriate model tier, and define tests or manual checks for the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shennawardana23/skillme/agentic-engineering
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 shennawardana23/skillme --skill agentic-engineering
Clone the repo
git clone --depth 1 https://github.com/shennawardana23/skillme

Made for: Claude Code.

Or install skillme, the plugin that ships this one along with the rest of its 137 skills, 2 commands.

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 agentic-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/shennawardana23/skillme/agentic-engineering/github.svg)](https://agentmods.dev/skills/shennawardana23/skillme/agentic-engineering)
Your own site
<a href="https://agentmods.dev/skills/shennawardana23/skillme/agentic-engineering"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/agentic-engineering/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 agentic-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/shennawardana23/skillme/agentic-engineering"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/agentic-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,446 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.
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 $0.00091 $0.01446
Opus 5 $0.00046 $0.00723
Sonnet 5 $0.00018 $0.00289
Haiku 4.5 $0.00009 $0.00145

Measured 8d ago against content hash 2fb8b88f1e7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agentic-engineering 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 8d 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.

skills/agentic-engineering/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Engineering

The engineering practice for a single unit of work when an AI agent does most of the typing and a human sets the goal, the constraints, and the acceptance bar. This is a per-task discipline — how you shape and check one piece of work — not the team-wide process changes (see ai-first-engineering for that).

Define done before you start

Write the completion criteria before the agent starts implementing, not after reviewing what it produced. If you can't state a concrete pass/fail condition, you don't yet know what "done" means well enough to hand the task off — decompose or clarify further first.

  • A capability check: what new behavior must exist and how would you demonstrate it (a test, a manual repro, a script).
  • A regression check: what existing behavior must not change.
  • An explicit non-goal, if the task is easy to over-scope (e.g. "do not touch the payment retry logic in this pass").

Task decomposition: the 15-minute unit

Break work into units small enough that each one is independently verifiable. A good unit:

  • has a single dominant risk — one thing that's actually hard about it, not three unrelated hard things bundled together
  • has a clear done condition you can check without re-reading the whole diff
  • can be verified on its own — you shouldn't need three other in-flight units to know whether this one is correct

If you can't articulate the unit's dominant risk in one sentence, it's still two units pretending to be one — split it.

Eval-first loop

  1. Define the capability eval (what should now work) and the regression eval (what must keep working) before implementation starts.
  2. Run both against the current code to get a baseline — capture what already fails and why, so you're not surprised by pre-existing gaps.
  3. Hand off the implementation.
  4. Re-run both evals and diff against the baseline. A capability eval that now passes plus a regression eval with no new failures is the actual completion signal — not the agent's own claim that it's done.

Read the full file on GitHub · 138 lines

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. 8d ago First seen · 138 lines · 91 tokens per session scan A 2fb8b88f1e7d

Subscribe to this mod's changes

agentic-engineering is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,446 once invoked, about $0.0005 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 2026-08-31.