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 fakoli/fakoli-plugins --skill start-prdgit clone --depth 1 https://github.com/fakoli/fakoli-pluginsWrote 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/fakoli/fakoli-plugins/start-prd)<a href="https://agentmods.dev/skills/fakoli/fakoli-plugins/start-prd"><img src="https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/start-prd/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/fakoli/fakoli-plugins/start-prd"><img src="https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/start-prd.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 | $0.00028 | $0.00373 |
| Opus 5.5 | $0.00011 | $0.00149 |
| Sonnet 5.5 | $0.00006 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
start-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 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.
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.
What it actually says
Start Prd
Resolve this plugin's installed root from the loaded skill path. Prefer its bin/fakoli-state launcher when no matching CLI is on PATH; run from the user's project or pass the command's --cwd argument. Read --help when a flag is uncertain. Use only tools exposed by the current host. For native MCP calls, supply the target project's absolute cwd; the server's startup directory is the installed package.
- Inspect the target project and any existing PRD before writing. Reuse requirements and decisions already supplied. When an existing draft is present, revise it rather than replacing it wholesale.
- Establish the problem, intended users, outcomes, non-goals, constraints and how success will be checked. Ask only consequential unanswered questions when the user is available; for an authorized autonomous run, record reasonable assumptions and unresolved decisions without waiting on cosmetic preferences.
- Use the PRD template, writing a reviewable draft to
.fakoli-state/prd.md. Preserve previous content through version control or an explicit backup when doing a rewrite. - Review the draft against the supplied brief, surface remaining decisions, and continue into parse/review via the prd skill when those steps are authorized. Do not require the user to type commands the host can execute.
This skill uses the current assistant and needs no separate API key. Optional external model inference belongs to the CLI's configured provider workflow. Invoke another brainstorming skill only if it is available and helpful; its mere installation does not make it mandatory.
See README for setup and the full CLI/MCP surfaces.
What ships with it
1 file 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.
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 Changed · -221 lines · -105 tokens per session 2ab2aa8cb7b2
- 1mo ago First seen · 239 lines · 133 tokens per session scan A 776a4ca4ff2f
start-prd is a skill published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 28d ago), licensed MIT. It adds 28 tokens to every session and 373 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
audit
Read-only quality gate that audits already-built work against its stated requirement and Definition of Done before it is allowed to move to 2done/. Produces a severity-ranked decision proposal (BLOCKER/MAJOR/MINOR/NIT) with evidence; the judgement never edits, only a recorded post-audit step may fix small findings.…
pr-vetting
Use when the user wants to thoroughly investigate, vet, review, or security-scan a pull request before deciding how to handle it - especially PRs from external or unknown contributors. Runs a parallel multi-agent investigation (technical, security, value/fit, contributor reputation) and merges the findings into one…
issue-triage
Use when the user wants to triage GitHub issues - decide whether an issue is still relevant, reproducible, closeable, a duplicate, or what concretely needs doing. Selects and prioritizes first (never dumps all issues at once), then deep-triages the chosen issues via parallel subagents, recommends actions for the owner…
requirements-verbatim
Capture a user requirement, decision, approval, or constraint word-for-word into an append-only dated log so it survives context compaction and can never be trimmed, softened, or reinterpreted. Use whenever the user states or approves a requirement, gives a GO, sets a constraint, or makes any decision that later work…
diag
Read-only root-cause diagnosis for a symptom, bug, failure, or unexpected behavior. Establishes the mechanism at file:line and reads up the facts instead of guessing, before any fix is attempted. Produces a diagnosis report; the fix is always a separate step gated by an explicit GO. Use when something is broken…
sandbox
Do WRITING pre-work for a clarify item that is blocked by a knowledge gap - a missing measurement, a mockup, or a feasibility proof - WITHOUT touching production code, without git, and without disturbing the task / build agent. Use when a 1clarify item cannot be answered by a product decision alone but needs something…