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-phase-contract-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-phase-contract-audit)<a href="https://agentmods.dev/skills/velinussage/brand-gen/brand-gen-phase-contract-audit"><img src="https://agentmods.dev/badge/skills/velinussage/brand-gen/brand-gen-phase-contract-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-phase-contract-audit"><img src="https://agentmods.dev/badge/skills/velinussage/brand-gen/brand-gen-phase-contract-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 | $0.00180 | $0.01953 |
| Opus 5.5 | $0.00072 | $0.00781 |
| Sonnet 5.5 | $0.00036 | $0.00391 |
| Haiku 4.5 | $0.00018 | $0.00195 |
Grade A, and why
brand-gen-phase-contract-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 2mo 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 — 145 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 Phase Contract Audit
Risk addressed: the in-process contract between pipeline phases is argparse.Namespace. There are 426 getattr(args, ...) call sites across 16 modules. PipelineRequest.build_scratchpad_namespace (pipeline_request.py:332) hand-builds a Namespace with ~30 fields just to pass typed data between in-process stages. getattr(args, "field", None) swallows typos, so renames silently zero out values. New fields require parallel updates in PIPELINE_MCP_PROPERTIES, PipelineRequest, from_mapping, build_scratchpad_namespace, the CLI builder, and per-phase getattr calls. Tests pass argparse.Namespace() so phantom fields slip through.
PlanDraft and GenerationScratchpad dataclasses exist but _run_scratchpad operates on the dict payload and converts at the end via scratchpad_from_dict. The _filter_fields helper (pipeline_types.py:386) silently drops unknown keys.
What this skill produces
{
"summary": {
"total_getattr_sites": 426,
"phantom_fields": 17,
"phases_with_drift": 4,
"fields_declared_but_unused": 8,
"namespace_fields_total": 73,
"typed_request_fields_total": 41
},
"phases": [
{
"phase": "route",
"consumed_fields": ["route_brief", "material_type", "render_backend", ...],
"declared_in": ["PipelineRequest"],
"phantom_in_phase": [],
"untyped_via_namespace_only": ["route_force"]
},
{
"phase": "plan",
"consumed_fields": [...],
"declared_in": ["MaterialPlan", "PipelineRequest"],
"phantom_in_phase": ["legacy_inspiration_seed"],
"untyped_via_namespace_only": ["accept_inspiration_recommendations"]
}
/* ... per-phase ... */
],
"phantom_fields_detail": [
{
"field": "legacy_inspiration_seed",
"read_at": ["plan_builder.py:412"],
"never_written_at": "no PipelineRequest entry, no Namespace builder line",
"default_returned": "None",
"blast_radius": "silent — production has never set this; renames break nothing but the field is dead"
}
],
"filter_fields_drift": [
{
"field": "branch_id",
"declared_in": "MaterialPlan, GenerationScratchpad",
"missing_from": "scratchpad_from_dict input shape",
"behavior": "silently dropped at deserialization"
}
],
"duplicate_field_routing": [
{
"field": "design_variance",
"paths": ["PipelineRequest.design_variance", "Namespace.design_variance", "scratchpad payload.design_variance"],
"consistency": "ok"
}
]
}
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.
- 2mo ago First seen · 145 lines · 180 tokens per session scan A cea04ca57f73
brand-gen-phase-contract-audit is a skill published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 5mo ago), licensed MIT. It adds 180 tokens to every session and 1,953 once invoked, about $0.0007 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.
brand-gen-phase-contract-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brand-gen-phase-contract-auditvelinussage/brand-gen | Skill | 0 | 5mo ago | MIT | A | 180 | Claude Code, Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | today | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | yesterday | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 321 | today | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | today | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 2.0k | yesterday | MIT | A | 36 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | today | none | A | 76 | Claude Code, Codex |