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 OutlineDriven/outline-driven-development --skill cpu-pipelines-and-hazardsgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/cpu-pipelines-and-hazards)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/cpu-pipelines-and-hazards"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cpu-pipelines-and-hazards/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/outlinedriven/outline-driven-development/cpu-pipelines-and-hazards"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cpu-pipelines-and-hazards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.01052 |
| Opus 5 | $0.00023 | $0.00526 |
| Sonnet 5 | $0.00009 | $0.00210 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
cpu-pipelines-and-hazards 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CPU pipelines and hazards
Contract
| Field | Bound contract |
|---|---|
| Trigger | A stall counter needs interpreting, instruction order changes throughput in a hot loop, or assembly scheduling needs relating to hardware behavior. |
| Authority | Read-only. The skill runs perf stat on a user-named binary and answers in chat. Nothing on disk changes, so there is nothing to roll back. No remote mutation. |
| Side effect | Chat output only. |
| Done | The hazard class in the loop is named, the counter that shows it is quoted where a binary exists, and one restructuring is proposed with its condition. |
Inputs
- Hot loop (required): source or assembly.
- Binary and workload (optional): needed for counter evidence.
- Target microarchitecture (optional): in-order embedded core or out-of-order desktop or server core. The answer differs.
Procedure
- Set the model. The five-stage in-order pipeline (fetch, decode, execute, memory, writeback) overlaps instruction N in execute with N+1 in decode. Out-of-order cores rename registers, issue to several ports, and retire in order; the five-stage picture still explains where a dependency costs. Done when: the user knows which model applies to the target.
- Classify the hazard. Done when: each dependency in the loop has a class.
| Hazard | Example | Hardware answer |
|---|---|---|
| Read after write (true dependency) | add r1, r2, r3 then sub r4, r1, r5 |
Forwarding from the execute or memory stage; a stall when the producer is a load |
| Write after read or write after write | Rare in an in-order core; matters under out-of-order rename | Register renaming |
| Control | A branch whose target is unknown until execute | Prediction, then a flush on mispredict; cost scales with pipeline depth |
| Structural | One memory port shared by two loads | Stall with no dependency at all |
- Break the dependency chain where the loop is latency-bound. A single accumulator serializes every iteration on the add latency. Two or more accumulators expose independent chains and let the core issue them in parallel. Done when: the loop is restructured or the user confirms the loop is memory-bound and the change would not help.
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.
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.
- 3d ago First seen · 76 lines · 47 tokens per session scan A b7b6bb3a89b1
cpu-pipelines-and-hazards is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,052 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
smt-solving-with-z3-cvc5
Use when a query needs direct SMT solving, an unsat core needs debugging, or another tool reports a solver timeout or unknown. Not for deciding what to prove: use proof-driven.
dimensional-analysis
Use when code mixes units, fixed-point precisions, scaling factors, rates, prices, shares, or conversions. Not for type-level unit modeling: use type-driven.
anomaly-driven-abduction
Tactic: Inductive/abductive path — describe anomalous phenomena, generate candidate explanations, rank by plausibility.
experiment-craft
Use this skill when the user wants to debug, diagnose, or systematically iterate on an experiment that already exists, or when they need a structured experiment log for tracking runs, hypotheses, failures, results, and next steps during active research. Apply it to underperforming methods, training that will not…
numerical-stability
Analyze and enforce numerical stability for time-dependent PDE simulations. Use when selecting time steps, choosing explicit/implicit schemes, diagnosing numerical blow-up, checking CFL/Fourier criteria, von Neumann analysis, matrix conditioning, or detecting stiffness in advection/diffusion/reaction problems.
hi-c-map-artifact-validation
Use when after executing the Juicer pipeline on raw Hi-C FASTQ files, to confirm that the pipeline has generated the expected .hic output artifact and that the contact matrix construction and normalization steps completed without error.