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 nospicyplease/amazon-ppc-advanced-skills --skill case-camouflage-skillgit clone --depth 1 https://github.com/nospicyplease/amazon-ppc-advanced-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/nospicyplease/amazon-ppc-advanced-skills/case-camouflage-skill)<a href="https://agentmods.dev/skills/nospicyplease/amazon-ppc-advanced-skills/case-camouflage-skill"><img src="https://agentmods.dev/badge/skills/nospicyplease/amazon-ppc-advanced-skills/case-camouflage-skill/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/nospicyplease/amazon-ppc-advanced-skills/case-camouflage-skill"><img src="https://agentmods.dev/badge/skills/nospicyplease/amazon-ppc-advanced-skills/case-camouflage-skill.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 | $0.00086 | $0.00908 |
| Opus 5 | $0.00043 | $0.00454 |
| Sonnet 5 | $0.00017 | $0.00182 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
case-camouflage-skill 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case Camouflage Skill
Use this skill when preparing Amazon Ads optimization output that may be shown to users, reviewers, public repos, demos, recordings, docs, or evals. The job is to camouflage the case context: keep optimization math real and exact while masking only user-facing labels and source-derived identifiers.
Non-Negotiables
- Preserve exact KPIs and optimization logic. Do not fake, redact, perturb, swap, incorrectly merge, or round metrics for privacy.
- Analyze first with raw source IDs. Group, rank, attribute, diagnose, and decide before masking. Never group by masked handles.
- Mask display-plane labels and identifiers: account/profile/project names, products, ASINs, SKUs, campaigns, ad groups, keywords, search terms, targets, placements, filenames, URLs, and source-derived identifiers.
- Use stable tenant/profile-scoped handles such as
ACCOUNT-000001,PROFILE-000001,PRODUCT-000001,ASIN-000001,CAMPAIGN-000001,KW-000001, andTARGET-000001. - Do not expose registry mappings, real customer data, source IDs, credentials, raw reports, private execution manifests, HMAC digests, or raw API readbacks in public output.
- Do not directly mutate Amazon Ads. You may create masked approval packets and private execution manifests for a separate approved execution tool after explicit approval.
Workflow
- Confirm scope: tenant/profile, marketplace, date windows, available reports, requested output surface, and whether this is public/demo/recording output.
- Load or configure a tenant-scoped masking registry. If text-only identifiers are present, require a per-tenant HMAC secret. See registry.
- Run the optimization in the analytical plane using raw source IDs and exact metrics. See metrics.
- Resolve display handles only after analysis. See masking.
- Build a masked approval packet for recommended actions. Keep private execution manifests in ignored private paths only. See approvals.
- Scan public artifacts, logs, stdout/stderr, rationales, readbacks, metadata, hidden sheets, and filenames before release. See artifact/log safety.
- Report coverage with counts and statuses only, never mappings. See coverage.
What ships with it
10 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.
- agents/openai.yaml 431 B
- references/approvals.md 798 B
- references/artifact-log-safety.md 791 B
- references/codename-resolution.md 543 B
- references/coverage.md 840 B
- references/lifecycle.md 566 B
- references/masking.md 1.2 KB
- references/metrics.md 984 B
- references/registry.md 1.1 KB
- references/style.md 597 B
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 · 53 lines · 86 tokens per session scan A 0aa57d053dfa
case-camouflage-skill is a skill published in the GitHub repository nospicyplease/amazon-ppc-advanced-skills (14 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 908 once invoked, about $0.0004 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
zach-product-research
A Sorftime-based product research skill for finding Amazon market opportunities and deciding whether a new product is worth pursuing. Sorftime is a market-research data source for Amazon sellers.
zach-seller-skill-creator
A Chinese-language guide for Amazon sellers who want to turn repeated work processes into reusable skills for an AI agent.
zach-listing-health-checker
An Amazon listing health checker that examines a product page as a shopper would see it, including visibility, price, seller, cart, delivery, category, rank, reviews, and search visibility.
zach-feature-demand-validator
A research skill for checking whether a small product improvement matches real customer demand. It compares product reviews, search keywords, and discussions in online communities.
zach-search-term-analyzer
An analyzer for Amazon Brand Analytics Top Search Terms reports, which show popular searches across Amazon and how clicks and conversions are distributed among products.
sealeap-amazon-apparel-lifecycle-ads
A playbook for planning advertising on Amazon US for clothing products, using an ASIN lifecycle. An ASIN is Amazon's product identifier; the lifecycle describes whether a product is new, growing, mature, declining, or seasonal.