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 The01Geek/prflow --skill specsgit clone --depth 1 https://github.com/The01Geek/prflowWrote 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/the01geek/prflow/specs)<a href="https://agentmods.dev/skills/the01geek/prflow/specs"><img src="https://agentmods.dev/badge/skills/the01geek/prflow/specs.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 19 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00125 | $0.00957 |
| Opus 5 | $0.00063 | $0.00478 |
| Sonnet 5 | $0.00025 | $0.00191 |
| Haiku 4.5 | $0.00013 | $0.00096 |
Grade A, and why
specs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 18 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forward to create-issue
/prflow:specs is a thin forwarding alias for /prflow:create-issue. Open skills/create-issue/SKILL.md with your file-read tool and follow it exactly, as if /prflow:create-issue had been invoked — but before you resolve any reference file create-issue names, read and apply the reference-base redirect below, because it governs where those references resolve and skipping it silently degrades the run. The create-issue root you open performs the one prompt-extension load for both command names — it reads the create-issue.md extension file — and the specs alias loads none of its own.
Reference-base redirect (load-bearing). The runner leaves the skill base directory (${CLAUDE_SKILL_DIR}) pointing at skills/specs/ even after you open create-issue as a plain file, so create-issue's own reference paths would otherwise resolve to a nonexistent skills/specs/references/ and silently degrade onto its reference-load-failure arms. Resolve create-issue's reference files from skills/create-issue/references/, and resolve any path create-issue derives from its own skill directory against skills/create-issue/ — never the invoked skills/specs/. Helpers reached through the ../../scripts/ suffix, and prompt extensions named by a literal skill name, are unaffected.
Resolve those create-issue targets portably, not as bare working-directory-relative paths — in an installed consumer checkout the working directory is the consumer's own project (which has no skills/ tree), while the plugin's skills live beside ${CLAUDE_SKILL_DIR}. Because ${CLAUDE_SKILL_DIR} is skills/specs/, its sibling create-issue directory is ${CLAUDE_SKILL_DIR:-<absolute skill base directory this runner reports in context>}/../create-issue/; resolve create-issue's SKILL.md and every reference path under it relative to that sibling directory (when ${CLAUDE_SKILL_DIR} is empty, take the create-issue sibling of the skill base directory the runner reports in context — never that base directory itself, which is the invoked specs directory) so both the initial open of create-issue's skill file and its reference loads resolve in a consumer checkout and not only in PRFlow's own dev tree.
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.
- today Changed · -10 lines 0f8f9dbe6917
- yesterday Changed beffb3d489b3
- 4d ago First seen · 28 lines · 125 tokens per session scan A 1c8a0371d8ce
specs is a skill published in the GitHub repository The01Geek/prflow (115 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 957 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
taiyi-review
A pre-merge review guide for checking code changes, design decisions, tests, and documentation. A merge adds reviewed changes to the main code branch.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
taiyi-requirement
A requirements-analysis process that turns a proposed change into a REQUIREMENT.md document. It records user needs, acceptance checks, terminology, triggers, and dependencies, with different levels of detail for different project sizes.
taiyi-change
A TaiyiForge workflow stage for writing a change proposal in CHANGE.md, with checks for scope, risks, success criteria, and related project documents.