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 velinussage/brand-gen --skill brand-gen-truncation-auditgit clone --depth 1 https://github.com/velinussage/brand-genWrote 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/velinussage/brand-gen/brand-gen-truncation-audit)<a href="https://agentmods.dev/skills/velinussage/brand-gen/brand-gen-truncation-audit"><img src="https://agentmods.dev/badge/skills/velinussage/brand-gen/brand-gen-truncation-audit/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/velinussage/brand-gen/brand-gen-truncation-audit"><img src="https://agentmods.dev/badge/skills/velinussage/brand-gen/brand-gen-truncation-audit.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 | $0.00203 | $0.01939 |
| Opus 5 | $0.00102 | $0.00970 |
| Sonnet 5 | $0.00041 | $0.00388 |
| Haiku 4.5 | $0.00020 | $0.00194 |
Grade A, and why
brand-gen-truncation-audit 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 11d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
For Sage brand work in Pi, use the paste-ready prompt at docs/prompts/pi-sage-brand-gen-full-pipeline.md. Keep this link instead of copying the full prompt into skill bodies.
Brand-Gen Truncation Audit
Risk addressed: prompt assembly applies caps through 6+ layers in sequence (per-part cap_text_at_sentence → joined-prelude cap → compress_prompt_body → evict_to_budget over PromptBlocks → execution-prompt re-cap → ad-hoc [:N] slices). Most truncation is silent — only review_prompt_architecture reports dropped blocks. Hard-coded limits live as magic numbers across 14+ files. The priority-tier PromptBlock machinery (prompt_block.py) only sees content after earlier caps already fired.
What this skill produces
A single JSON-shaped manifest of cap sites. Each entry:
{
"site_id": "prompt_assembly.py:387",
"kind": "cap_text_at_sentence | compress_prompt_body | evict_to_budget | hard_slice | summarize | strip",
"stage": "per_part | combined_prelude | body | execution | post_block_eviction",
"input_field": "brand_anchor_rule | inspiration_directive | copy_bank | …",
"limit_value": 480,
"limit_source": "constant:NON_INTERFACE_BODY_CAP | json:data/prompt_budget.json#interface | literal:480 | literal:[:5]",
"configurable": true,
"tracked": true,
"tracked_via": "dropped_blocks | recommendation_string | none",
"fires_before_priority_system": false,
"snippet": "cap_text_at_sentence(brand_anchor_rule, NON_INTERFACE_BODY_CAP)"
}
Plus a summary: total sites, silent vs tracked ratio, sites firing before evict_to_budget, hard-coded literal counts by file.
When to use
- Before adjusting
data/prompt_budget.json— to know which caps actually respect it. - Before promoting a new
PromptBlockpriority — to know which caps would defeat it. - When
iteration_memory.jsonkeeps losing entries that the agent expected to survive. - When the rendered prompt visibly drops a section the planner asked for but
dropped_blocksis empty. - When introducing a new prompt section, to choose where its cap should live.
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.
- 11d ago First seen · 121 lines · 203 tokens per session scan A e493e96ad607
brand-gen-truncation-audit is a skill published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 3mo ago), licensed MIT. It adds 203 tokens to every session and 1,939 once invoked, about $0.0010 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
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…