prompt-and-session-engineering

prompt-and-session-engineering is a skill for Claude Code, Codex from jxoesneon/Ciel. It costs 17 tokens per session (482 once invoked), scanned A, original, Apache-2.0.

A framework for improving prompts and managing long coding-agent sessions. It also breaks large projects into smaller prompts for research, implementation, and review.

In plain words
What is it for?
It is for refining task prompts, choosing workflows, splitting epics into phases, tracking session budgets, and creating branches before risky work.
Why use it?
It reduces missing context, unfocused sessions, lost history, and unclear instructions to the coding agent.

Skill for Claude CodeCodex

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

Good fit It is for refining task prompts, choosing workflows, splitting epics into phases, tracking session budgets, and creating branches before risky work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jxoesneon/ciel/prompt-and-session-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 jxoesneon/Ciel --skill prompt-and-session-engineering
Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

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 prompt-and-session-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/jxoesneon/ciel/prompt-and-session-engineering/github.svg)](https://agentmods.dev/skills/jxoesneon/ciel/prompt-and-session-engineering)
Your own site
<a href="https://agentmods.dev/skills/jxoesneon/ciel/prompt-and-session-engineering"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/prompt-and-session-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 prompt-and-session-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/jxoesneon/ciel/prompt-and-session-engineering"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/prompt-and-session-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 482 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 $0.00017 $0.00482
Opus 5 $0.00009 $0.00241
Sonnet 5 $0.00003 $0.00096
Haiku 4.5 $0.00002 $0.00048

Measured 9d ago against content hash 6f1ee1702064, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prompt-and-session-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 9d 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/prompt-and-session-engineering/SKILL.md · 52 lines

What it actually says

CIEL ADAPTATION: Prompt & Session Engineering (The Craft Layer)

This skill manages the internal quality of instructions and the health of long-running sessions.

Prompt Optimization (Advisory)

  1. Diagnosis: Identify missing context (Tech stack, boundaries, criteria).
  2. Workflow Matching: Map the intent to CIEL commands (/plan, /tdd, /verify).
  3. Refinement: Output an optimized prompt that includes explicit scope, tech stack, and verification steps.
  4. Constraint: Advisory role ONLY. Prohibit executing the task; only provide the optimized text.

Session Hygiene (REPL)

  • Task Focus: Keep sessions focused on a single logical unit.
  • Branching: Branch the session (/branch) before performing high-risk or speculative changes.
  • Compaction: Compact history (/compact) after major milestones to preserve context for the final integration.
  • Metrics: Monitor token usage and budget burn per session.

Multi-Prompt Splitting (EPIC)

  • Prompt 1: Research + Plan (Architecture).
  • Prompt 2-N: Implement one phase per prompt (TDD).
  • Final Prompt: Integration + Security Review.

Anti-Patterns

  • Execution in Advice: Writing code inside a "Prompt Optimization" turn.
  • Amnesiac Resumption: Resuming a session without loading the previous decisions from context.json.
  • The Context Cliff: Ignoring history growth until the model starts hallucinating or truncating responses.
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. 9d ago First seen · 52 lines · 17 tokens per session scan A 6f1ee1702064

Subscribe to this mod's changes

prompt-and-session-engineering is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 17 tokens to every session and 482 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 2026-09-03.