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/rickygao/specrate/specratenpx skills add rickygao/specrate --skill specrategit clone --depth 1 https://github.com/rickygao/specrateWrote 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/rickygao/specrate/specrate)<a href="https://agentmods.dev/skills/rickygao/specrate/specrate"><img src="https://agentmods.dev/badge/skills/rickygao/specrate/specrate.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 | $0.00020 | $0.00546 |
| Opus 5 | $0.00010 | $0.00273 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
specrate 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 5d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specrate
Overview
The specrate system is designed to manage specs and changes to those specs in a structured manner. It provides a framework for proposing, planning, implementing, and archiving changes to the system's specs.
- PRINCIPLE.md must be read first to understand how specrate works.
- actions folder defines detailed steps for each specrate action.
- templates folder contains templates for various specrate artifacts and reports.
Decisions
Based on the user's request, decide which action to take.
- If the user intends to show the current status of specs and changes, follow SHOW-STATUS.md action.
- If the user intends to propose a new change, follow PROPOSE-CHANGE.md action.
- If the user intends to amend an existing change, follow AMEND-CHANGE.md action.
- If the user intends to plan a proposed change, follow PLAN-CHANGE.md action.
- If the user intends to implement a planned change, follow IMPLEMENT-CHANGE.md action.
- If the user intends to archive an implemented change, follow ARCHIVE-CHANGE.md action.
- If the user intends to fix a spec according to the codebase, follow FIX-SPEC.md action.
- If the user's intent mixes multiple actions, break down the intent into individual actions, ask for confirmation, and execute them one by one.
- If the user's intent is ambiguous (e.g., “update the spec”), ask a clarifying question with possible options to determine the specific action needed.
Disciplines
- Always ask for clarifications if needed, and ensure the workspace remains consistent after each step. When asking for clarifications, provide concise options to the user if applicable.
- All specrate-managed artifacts that this skill creates/updates in the user's repository MUST reside in the
.specrate/folder at the repository root. - Do NOT create auxiliary documents (README, index, etc.) outside
.specrate/unless explicitly instructed by the user.
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.
- 5d ago First seen · 45 lines · 20 tokens per session scan A 84da52d97741
specrate is a skill published in the GitHub repository rickygao/specrate (8 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 546 once invoked, about $0.0001 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
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
spec-kitty-mission-review
Review a fully merged Spec Kitty mission post-merge (all WPs done/approved) to verify spec→code fidelity, FR coverage, drift, risks, and security. Triggers: "review the merged mission", "post-merge mission review", "verify the completed mission", "audit the mission implementation", "mission-level acceptance review"…
spec-kitty-runtime-next
Drive the canonical spec-kitty next --mission control loop for mission advancement. Load agent profiles at init, apply action-scoped doctrine context at each step boundary, and pull specific tactics/directives on demand. Triggers: "run the next step", "what should runtime do next", "advance the mission", "what is the…
spec-kitty-mission-system
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 6-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…
spec-kitty-bulk-edit-classification
Recognize when a mission is a bulk edit and drive the occurrence-classification guardrail on the user's behalf. Triggers: user says any variant of "rename X to Y", "change the terminology", "migrate all occurrences", "replace across the codebase", "the X feature is now the Y feature", "sed everywhere", or any request…
spec-kitty-git-workflow
Understand how Spec Kitty manages git: what git operations Python handles automatically, what agents must do manually, worktree lifecycle, auto-commit behavior, merge execution, and the safe-commit pattern. Triggers: "how does spec-kitty use git", "worktree management", "auto-commit", "who commits what", "git…