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 Firstp1ck/pi-coding-agent-forge --skill requirements-engineeringgit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgeWrote 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/firstp1ck/pi-coding-agent-forge/requirements-engineering)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/requirements-engineering"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/requirements-engineering/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/firstp1ck/pi-coding-agent-forge/requirements-engineering"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/requirements-engineering.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 | $0.00042 | $0.04452 |
| Opus 5.5 | $0.00017 | $0.01781 |
| Sonnet 5.5 | $0.00008 | $0.00890 |
| Haiku 4.5 | $0.00004 | $0.00445 |
Grade A, and why
requirements-engineering 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 22d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements engineering
Help the project owner gather, document, check, agree, and manage requirements without substituting model output for stakeholder evidence or approval. Work iteratively. Do not impose elicitation, documentation, review, and alignment as a fixed phase sequence.
Every start, update, or resume ends with either a maintained requirements-engineering plan and its next ready step, or a concrete next-step guide. A plan is warranted only when the available evidence supports useful sequencing.
This skill provides guidance, not enforcement. Loading it does not install packages, contact people, approve requirements, authorize implementation, or change a project.
When to use
Use this skill for requests to:
- start requirements work for a software project or early product idea;
- update requirements after new evidence, a decision, or a scope change;
- resume interrupted requirements work from project records;
- assess whether a requirement is ready for implementation handoff;
- trace the impact of changing a source, decision, or requirement;
- prepare an interview guide, stakeholder survey, observation guide, workshop agenda, context summary, prototype feedback guide, or requirements review;
- explain requirements terminology or a technical requirements sentence in plain language.
Should trigger
- "Start requirements engineering for this empty project."
- "Resume the requirements work and show me the plans I can continue."
- "REQ-17 changed. Show the impact before updating the approved requirement."
- "Draft questions for interviewing support staff about return approvals."
- "What does system boundary mean for this project?"
Should not trigger
- "Implement REQ-17 and deploy it."
- "Fix this failing unit test."
- "Write general product marketing copy."
- "Give me legal approval for this compliance requirement."
- "Send this survey to all customers."
Requirements work may identify later implementation, but that does not authorize implementation. Route implementation, legal review, external contact, deployment, or unrelated document work to the appropriate workflow under the user's actual authorization. An explicit user implementation request is authority to assess that work in its own workflow; do not falsely say no request was made. This skill itself adds no permission and does not execute that work.
What ships with it
5 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.
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.
- 22d ago First seen · 289 lines · 42 tokens per session scan A 51ccb1cf1865
requirements-engineering is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (91 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 4,452 once invoked, about $0.0002 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 2026-09-25.
Other skills, from other repositories
swarm-plan
Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.
orchestrator
Use when somebody asks for an orchestrator, a lead agent, a coordinator, or somebody to "keep an eye on" the agents working on a project — and when asking about who is minding a project, who is blocked, or what the orchestrator last said. Puts a seat in a project's chair inside agentglass (with its own rules, queue…
issue-ingest
Full execution protocol for MODE: ISSUEINGEST -- GitHub issue intake, localization, spec generation, and transition to the full fix workflow.
phase-wrap
Claude Code adapter for MODE: PHASE-WRAP. Delegates to the canonical opencode-swarm phase boundary protocol.
gini-bug-report
File a locally-captured, already-redacted Gini crash report as a GitHub issue, with the user's consent. Reads the pending crash queue and delegates the actual filing to the github-issues skill.
opengeni-schedules
Create a schedule, recurring task, reminder, or monitor in Opengeni. Read this before turning a user's request into scheduled work, including Create with Opengeni from Schedules. Discover the required resources and integrations, then create the task with the user's cadence and time zone.