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 agentmods add skills/vshidlovsky/prd-agents-framework/create-prdnpx skills add vshidlovsky/prd-agents-framework --skill create-prdgit clone --depth 1 https://github.com/vshidlovsky/prd-agents-frameworkWrote 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/vshidlovsky/prd-agents-framework/create-prd)<a href="https://agentmods.dev/skills/vshidlovsky/prd-agents-framework/create-prd"><img src="https://agentmods.dev/badge/skills/vshidlovsky/prd-agents-framework/create-prd.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.11146 |
| Opus 5 | $0.00024 | $0.05573 |
| Sonnet 5 | $0.00010 | $0.02229 |
| Haiku 4.5 | $0.00005 | $0.01115 |
Grade A, and why
create-prd 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 4d 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 — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Creation Pipeline
Run the full PRD workflow for {argument}.
Arguments
{argument} is the initiative name, optionally followed by flags. Strip every flag before using {argument} as the initiative name — the initiative name is what remains, and it is what every file path, handoff name, and agent prompt uses.
| Flag | Values | Effect |
|---|---|---|
--tc |
slim | full |
Technical Contract mode for this run only. Overrides the project-context setting. |
Anything else after the initiative name is initiative brief text, not a flag — pass it through to Phase 0.
Pre-flight
-
Resolve the Technical Contract mode and store it as
TC_MODE, withTC_MODE_SOURCErecording where it came from. Precedence, highest first:--tc slim/--tc fullon this invocation →TC_MODE_SOURCE = run-override.claude/project-context.md→ PRD Configuration → Technical Contract → Mode →TC_MODE_SOURCE = project-contextslim→TC_MODE_SOURCE = default(also the answer for an older project-context.md that predates the setting)
Reject any
--tcvalue other thanslimorfull: STOP and tell the user the two valid values. Announce the resolution once, before Phase 0 — e.g. "Technical Contract mode: full (run override; project-context says slim)" — so the user can correct it before research burns tokens. Then passTC_MODEexplicitly to the writer, the reviewer, and the senior PM: the mode a document was written in is not re-derivable from the document, and an agent that re-resolves it from project-context.md silently loses the override. -
Read
.claude/project-context.md— confirm it exists and is filled in. If it doesn't exist, STOP and tell the user: "You need to set up.claude/project-context.mdfirst. Copy the template from the framework and fill it in for your project." -
Confirm the initiative directory exists or create it at the output path specified in project-context.md. Also create the
_artifacts/subdirectory:mkdir -p "{initiative_dir}/_artifacts" -
Read the Model Profile table from project-context.md. Extract the
Modelcolumn for each agent row. Store asMODEL_MAP— a lookup from agent name to model (e.g.,researcher → sonnet,prd-writer → opus,prd-senior-pm → fable). If the Model Profile section is missing, default all agents toopus— exceptprd-senior-pm, which defaults tofable. Pass every value through to the Agent spawn as-is:opus,sonnet,haiku, andfableare all valid tier names. Never rewritefableto another tier because it looks unfamiliar. -
Check if Run Logs are enabled in project-context.md. If enabled:
RUN_ID=$(date -u +%Y%m%d-%H%M%S) LOG_FILE=".claude/prd-run-log.jsonl" STATE_FILE="{initiative_dir}/_artifacts/.run-state.json" TIMING_FILE="{initiative_dir}/_artifacts/.run-timing.tmp" echo "pipeline_start=$(date +%s) $(date -u +%Y-%m-%dT%H:%M:%SZ)" > "$TIMING_FILE"Record the profile name (from the
Profilefield in Model Profile) for the run log.
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.
- 4d ago First seen · 598 lines · 49 tokens per session scan A 014bfad4b6a3
create-prd is a skill published in the GitHub repository vshidlovsky/prd-agents-framework (4 stars, last pushed 22d ago), licensed MIT. It adds 49 tokens to every session and 11,146 once invoked, about $0.0002 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
execute-task
Execute the next TaskMaster task using the implementation plan with CDD verification. Picks the next ready task, matches it to the plan step, implements via a dispatched subagent, verifies subtasks with evidence, marks the task done, and loops until every task is complete. Wraps the TaskMaster next -> in-progress ->…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…