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.
npx agentmods add skills/sifxprime/kodelyth-ecc/agentic-engineeringnpx skills add sifxprime/kodelyth-ecc --skill agentic-engineeringgit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote 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.
[](https://agentmods.dev/skills/sifxprime/kodelyth-ecc/agentic-engineering)<a href="https://agentmods.dev/skills/sifxprime/kodelyth-ecc/agentic-engineering"><img src="https://agentmods.dev/badge/skills/sifxprime/kodelyth-ecc/agentic-engineering.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00024 | $0.00358 |
| Opus 5 | $0.00012 | $0.00179 |
| Sonnet 5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
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 yesterday.
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.
This is a copy
92% identical to agentic-engineering — 25 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.
What it actually says
Agentic Engineering
Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.
Operating Principles
- Define completion criteria before execution.
- Decompose work into agent-sized units.
- Route model tiers by task complexity.
- Measure with evals and regression checks.
Eval-First Loop
- Define capability eval and regression eval.
- Run baseline and capture failure signatures.
- Execute implementation.
- Re-run evals and compare deltas.
Task Decomposition
Apply the 15-minute unit rule:
- each unit should be independently verifiable
- each unit should have a single dominant risk
- each unit should expose a clear done condition
Model Routing
- Haiku: classification, boilerplate transforms, narrow edits
- Sonnet: implementation and refactors
- Opus: architecture, root-cause analysis, multi-file invariants
Session Strategy
- Continue session for closely-coupled units.
- Start fresh session after major phase transitions.
- Compact after milestone completion, not during active debugging.
Review Focus for AI-Generated Code
Prioritize:
- invariants and edge cases
- error boundaries
- security and auth assumptions
- hidden coupling and rollout risk
Do not waste review cycles on style-only disagreements when automated format/lint already enforce style.
Cost Discipline
Track per task:
- model
- token estimate
- retries
- wall-clock time
- success/failure
Escalate model tier only when lower tier fails with a clear reasoning gap.
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.
- yesterday First seen · 64 lines · 24 tokens per session scan A c202c6bfe6c9
agentic-engineering is a skill published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 358 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to agentic-engineering, differing in 25 lines, and is treated as a copy.
Other skills, from other repositories
foolproof-product
Use this skill on ANY code change in codevira's product surface (mcpserver/, indexer/). Triggers on Edit/Write to product code, on phrases like "fix bug", "add feature", "handle error", or any modification to commands the end-user runs. Enforces 10 product- reliability principles: no silent failures, atomic state…
open-source-quality
Use this skill before committing, pushing, or opening a PR. Triggers on phrases like "commit", "git commit", "push", "open PR", "create pull request", "finalize this change". Enforces conventional commit messages, atomic commits, code style (ruff/mypy), public-API docstrings, actionable error messages, changelog…
epistemic-honesty
Use this skill whenever you're about to (1) make a definitive claim like "this works", "tests pass", "ready to ship", "fixed", "done"; or (2) propose a solution to a problem; or (3) diagnose a bug or issue. Forces explicit confidence calibration with inline evidence, surfaces what you don't know, and demands a…
release-readiness
Use this skill whenever the conversation mentions releasing, shipping, publishing, promoting to PyPI, "ship it", "release X.Y.Z", "ready to release", "let's publish", or any phrase suggesting moving codevira to production. Walks the 5-gate release gauntlet (G1-G5) and refuses to proceed without evidence at every gate.…
development-discipline
Use this skill before ANY code-writing tool call (Edit, Write, NotebookEdit) on this project. Triggers on phrases like "implement", "fix bug", "add feature", "refactor", "create function", "modify file", or whenever the user asks for a code change. Forces a 4-step CONTEXT → PURPOSE → REASON → CODE sequence with…
practical-coding
Use for implementing, fixing, refactoring, or reviewing code with the smallest correct change; routes only unresolved debugging, architecture/choice, or risk-boundary blockers, while code retrieval uses the cheapest sufficient available capability.