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 5.5 | $0.00056 | $0.00730 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 141 tokens to every session and 1,825 once invoked, about $0.0006 per session on Opus 5.5. 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
agent-challenges
Agent skill for challenges - invoke with $agent-challenges.
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.
continuous-learning
Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.
note
Generate study notes from a lecture transcript and slides. Runs transcript + slide download in parallel, then writes a Markdown note with timeline outline.
trans
Transcribe a single Tongji Look lecture video to SRT + TXT, optionally download slide snapshots in parallel.
list
Discover and select courses from Tongji Look (look.tongji.edu.cn). Lists recent or all courses, filters by keyword, and saves the chosen course for use with /trans, /note, and other commands. Prerequisite for all lecture workflows.