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 skills add jscraik/Agent-Skills --skill talk-jourdan-pipelines-to-promptsgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/talk-jourdan-pipelines-to-prompts)<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-jourdan-pipelines-to-prompts"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-jourdan-pipelines-to-prompts/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.
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-jourdan-pipelines-to-prompts"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-jourdan-pipelines-to-prompts.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00141 | $0.01825 |
| Opus 5 | $0.00071 | $0.00912 |
| Sonnet 5 | $0.00028 | $0.00365 |
| Haiku 4.5 | $0.00014 | $0.00183 |
Grade A, and why
talk-jourdan-pipelines-to-prompts 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
From Pipelines to Prompts: Surviving the Shift to AI — Panel (Stephane Jourdan, Simon, Samantha)
A practitioner panel of engineers who lived through cloud, DevOps, and DevSecOps transitions, now reflecting on the AI-native shift. Core thesis: the AI shift is more dramatic and faster-spreading than cloud-native because it forces every department to adapt, not just engineering. Teams that survive are those with disciplined feedback loops, rigorous harness engineering, and clear observability.
Panelists
- Stephane Jourdan — practitioner and panel moderator/contributor
- Simon (Saxo Bank) — engineering perspective from a financial services context
- Samantha — practitioner focused on operational and organisational dimensions
Panel-Specific Concept Framings
These are the definitions and framings as used by the panelists — note where they diverge from common usage.
- Harness Engineering: Treated as a first-class engineering discipline, not an afterthought — encompasses prompt templates, guardrails, input/output validation, and feedback mechanisms making AI behaviour testable and improvable.
- Co-Driving vs. Self-Driving: The panel's framing for the spectrum of human oversight — co-driving (AI augments human decisions) vs. self-driving (autonomous in production). Panelists debated the appropriate point on this spectrum given organisational maturity.
- Reflector Agents: Agents that observe their own outputs and production behaviour to surface anomalies or drift — framed as a mechanism for closing the feedback loop without constant human review.
- Self-Learning Production Agents: Agents that incorporate production feedback signals to refine their own behaviour. Panelists highlighted governance requirements and risks of allowing agents to self-modify.
- Observability (AI-adapted): Beyond traditional APM — requires new primitives such as prompt/response logging, token-level tracing, and semantic drift detection. Emphasised especially by Simon in the Saxo Bank context.
- Feedback Loops: The panel's primary differentiator between teams that improve vs. stagnate — structured capture of production signals (user feedback, error rates, downstream outcomes) routed back into evaluation or prompt refinement.
What ships with it
4 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.
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.
- 12d ago First seen · 113 lines · 141 tokens per session scan A 0f34b448e052
talk-jourdan-pipelines-to-prompts is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 141 tokens to every session and 1,825 once invoked, about $0.0007 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.
Other skills, from other repositories
ai-education-data-explorer
An education-data analysis helper for interpreting teaching or recruitment data. It turns supplied data into a diagnosis, improvement suggestions, and scoring or activity checklists.
ai-educational-research-methods
An education-research methods review helper for checking whether a study uses a suitable research method. It creates teaching or hiring feedback, improvement suggestions, and checklists from supplied material.
ai-upskilling-training-diagnosis
A business-diagnosis assistant that turns provided information into a summary, findings, and recommended actions.
course-landing-page-conversion-review
A conversion experiment review assistant for evaluating changes to an online course landing page. A landing page is a focused web page designed to persuade visitors to take an action, such as enrolling.
course-outline-market-positioning
A business diagnosis assistant for evaluating course ideas and their market positioning using supplied information.
lesson-plan-activity-designer
An activity-design assistant for creating or reviewing learning activities. The available description identifies it as a visual-quality diagnosis tool, so its exact activity-design capabilities are not fully specified.