Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add infraspecdev/tesseract/plugin install shieldWrote 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/infraspecdev/tesseract/prd-docs)<a href="https://agentmods.dev/skills/infraspecdev/tesseract/prd-docs"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/prd-docs/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/infraspecdev/tesseract/prd-docs"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/prd-docs.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 | $0.00139 | $0.05422 |
| Opus 5.5 | $0.00056 | $0.02169 |
| Sonnet 5.5 | $0.00028 | $0.01084 |
| Haiku 4.5 | $0.00014 | $0.00542 |
Grade C, and why
prd-docs scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
[y] Run: curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
[y] Run: curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Docs
Author a new PRD with the Shield 20-section problem-first scaffold (or 10-section lean variant), or upgrade an existing lean PRD to standard by adding missing sections.
Output Path — MANDATORY
{output_dir}/{feature}/
├── prd.md ← registry: {prd} = {feature_dir}/prd.md
├── outputs/prd.html ← registry: {prd_html} = {feature_outputs}/prd.html
└── prd.meta.json ← side-artifact (metadata sidecar, not in registry)
Where {output_dir} comes from .shield.json and {feature} is the feature folder. Numbered run subfolders (prd/{N}-{slug}/) are gone — prd.md lives flat in the feature folder.
prd.meta.json is metadata (records type, status, owner, last_updated, rubric_version, and linked_plans auto-populated by /plan) — it is a side-artifact like the manifest, not a primary deliverable, so it is not in the outputs: registry.
When to Use
- User invokes
/prdto author a new PRD - User invokes
/prdin a feature folder containing a lean PRD (triggers upgrade flow)
When NOT to Use
- Review an existing PRD — use
/prd-reviewinstead - Generate a plan from a PRD — use
/planinstead - Capture pre-PRD context — use
/researchinstead
Step Skeleton
| Step | Action | Condition | Mandatory |
|---|---|---|---|
| 1 | Read .shield.json for prd_template, prd_required_sections |
always | Yes |
| 2 | Resolve feature folder context | always | Yes |
| 3 | Check for prior PRD in feature folder (lean → trigger upgrade flow) | only if prior PRD exists | conditional |
| 4 | Ask user for PRD type (standard | lean) | always |
| 5 | Check for prior /research transcript; pre-populate Problem/Personas/Dependencies if present; note glossary rows for §2 Terminologies (step 13) |
only if research exists | conditional |
| 6 | Walk Section 1 (Header) | always | Yes |
| 6a | Insert empty Terminologies placeholder for §2; fill later (step 13) | always | Yes |
| 7 | Walk Sections 3, 4 (Problem, Personas) | always | Yes |
| 7a | Walk Section 5 (Architecture & flows) — optional; user adds Mermaid blocks / image links, or leaves empty | always | Yes |
| 8 | Walk Section 6 (Goals) | always | Yes |
| 9 | Invoke shield:story-coverage between Sections 6 and 8 — scaffold expected stories |
standard only | conditional |
| 10 | Walk Section 7 (Metrics) and Section 8 (Stories with Type prompt) | always (lean: only §7) | Yes |
| 11 | Invoke shield:milestone-coverage between Sections 8 and 15 (standard) or after Section 7 (lean) |
always | Yes |
| 12 | Walk Section 15 rollout-mechanics; Sections 16..20 (standard) or §9, §10 (lean) | standard only for §15-§20 | conditional |
| 13 | Build Terminologies (§2) — research-glossary copy + LLM scan of drafted body, user confirms | always | Yes |
| 14 | Apply custom-template merging if .shield.json.prd_template is set |
only if config set | conditional |
| 14b | Apply shield:writing-style to all author-written prose (NOT rendered/marker-wrapped sections or the §2 Terminologies table values) before writing |
always | Yes |
| 15 | Write prd.md, prd.html, prd.meta.json |
always | Yes |
| 16 | Update manifest, regenerate index.html | always | Yes |
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.
- meta-schema.md 3.4 KB
- templates.md 8.8 KB
- test-fixtures/lean-upgrade-prior-prd.md 1.4 KB
- test-fixtures/new-from-scratch-expected.md 16 KB
- test-fixtures/with-milestones-lean.md 3.5 KB
- test-fixtures/with-milestones-standard.md 12 KB
- test-fixtures/with-research-transcript-expected.md 14 KB
- test-fixtures/with-research-transcript.md 4.2 KB
- test-fixtures/without-milestones.md 8.2 KB
- type-detection.md 1.7 KB
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.
- 1mo ago First seen · 363 lines · 139 tokens per session scan C d4ef9193bf1f
prd-docs is a skill published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 3mo ago), licensed MIT. It adds 139 tokens to every session and 5,422 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…