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 benjaminard/fable-skills --skill outcome-first-writinggit clone --depth 1 https://github.com/benjaminard/fable-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/benjaminard/fable-skills/outcome-first-writing)<a href="https://agentmods.dev/skills/benjaminard/fable-skills/outcome-first-writing"><img src="https://agentmods.dev/badge/skills/benjaminard/fable-skills/outcome-first-writing/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/benjaminard/fable-skills/outcome-first-writing"><img src="https://agentmods.dev/badge/skills/benjaminard/fable-skills/outcome-first-writing.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 | $0.00068 | $0.00665 |
| Opus 5 | $0.00034 | $0.00332 |
| Sonnet 5 | $0.00014 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
outcome-first-writing 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 10d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outcome-First Writing
Lead with the answer. Shorten by cutting content, never by compressing prose. Readability beats brevity every time the two conflict.
Lead with the outcome
Your first sentence answers "what happened" or "what did you find": the thing the reader would ask for if they said "just give me the TLDR." Supporting detail and reasoning come after, for readers who want them. Never open with background, method, or throat-clearing; the reader who needs context will keep reading, but the reader who needs the answer should not have to hunt.
Selectivity over compression
There are two ways to make writing shorter, and only one of them works:
- Selectivity (correct): drop whole points that do not change what the reader thinks or does next. Fewer things, said fully.
- Compression (wrong): keep every point but squeeze the prose into fragments, abbreviations, arrow chains like
A → B → fails, and jargon. Everything, said badly.
Compressed text saves the writer's tokens by spending the reader's time. If the reader has to re-read a sentence, or ask what a term means, every second the brevity saved is gone. What you keep, write in complete sentences with the technical terms spelled out.
The formatting budget
Formatting is not organization. Prose is the default.
- Headers belong only in genuinely sectioned documents. A conversational answer, however substantive, is paragraphs.
- Bullets are for lists of parallel items. Argument, explanation, and narrative are prose; a chain of reasoning chopped into bullets loses exactly the connective tissue that made it reasoning.
- Tables hold short enumerable facts. Explanations go in the surrounding prose, not crammed into cells.
- Bold marks the one thing that must survive a skim, which means it loses all meaning when applied per-sentence.
If every response you write has headers, bullets, and a bolded phrase per paragraph, the formatting is a tic, not a choice.
Kill the tells
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.
- 10d ago First seen · 45 lines · 0 tokens per session scan A 0ec5df23884d
outcome-first-writing is a skill published in the GitHub repository benjaminard/fable-skills (30 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 665 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
alterlab-paper-writer
Drafts and revises academic papers through a 12-agent pipeline with hardened LaTeX output (apa7 document class, justified text, table column-width formula, centered bilingual abstracts, standardized font stack, PDF compiled from LaTeX), supporting IMRaD, literature review, theoretical, case study, policy brief, and…
alterlab-pyhealth
Develops, tests, and deploys clinical machine learning models with the PyHealth healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare…
alterlab-imaging-data-commons
Query and download public cancer imaging data from the NCI Imaging Data Commons (IDC) using the idc-index Python package, filtering by metadata, visualizing in-browser, and checking licenses, with no authentication required. Use when obtaining large-scale radiology (CT, MR, PET) or digital pathology DICOM datasets for…
alterlab-phylogenetics
Build phylogenetic trees end-to-end from raw sequences — MAFFT multiple sequence alignment, optional TrimAl trimming, IQ-TREE 2 maximum-likelihood inference with model selection and bootstraps, FastTree for large datasets, then visualize with ETE3 or FigTree. Use when reconstructing trees from sequences (FASTA) for…
alterlab-molecular-dynamics
Runs and analyzes molecular dynamics simulations with OpenMM and MDAnalysis — setting up protein and small-molecule systems, assigning force fields, running energy minimization and production MD, and analyzing trajectories (RMSD, RMSF, contact maps, free energy surfaces). Use when simulating protein or ligand…