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 loiane/specs-driven-development-spring-angular --skill ears-spec-authoringgit clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angularWrote 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/loiane/specs-driven-development-spring-angular/ears-spec-authoring)<a href="https://agentmods.dev/skills/loiane/specs-driven-development-spring-angular/ears-spec-authoring"><img src="https://agentmods.dev/badge/skills/loiane/specs-driven-development-spring-angular/ears-spec-authoring/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/loiane/specs-driven-development-spring-angular/ears-spec-authoring"><img src="https://agentmods.dev/badge/skills/loiane/specs-driven-development-spring-angular/ears-spec-authoring.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 | $0.00058 | $0.01049 |
| Opus 5.5 | $0.00023 | $0.00420 |
| Sonnet 5.5 | $0.00012 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
ears-spec-authoring 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EARS-lite spec authoring
The five shapes
Every AC is one of:
| Shape | Skeleton | Use when |
|---|---|---|
| Ubiquitous | The system shall <response>. |
Always-true invariant. |
| Event-driven | When <trigger>, the system shall <response>. |
An external event causes a behavior. |
| State-driven | While <state>, the system shall <response>. |
Behavior holds throughout a state. |
| Optional feature | Where <feature included>, the system shall <response>. |
Conditional on configuration. |
| Unwanted behavior | If <unwanted condition>, then the system shall <mitigation>. |
Error / failure handling. |
Rules (enforced by spec-review.md)
- One AC = one condition + one outcome. Split anything with "and".
- Stable IDs. Format
AC-NNN. Never renumber. Insertions get the next number, even if it breaks reading order. - No implementation. No class names, no DB columns, no library names, no defaults.
- No vague NFRs. "Fast" →
< 200 ms p95 under 50 RPSOR demote toQ-NNN. - No silent defaults. If the user did not say which behavior to pick, write a
Q-NNN. - Feature-flag the risky cutovers. For any cutover, migration, or behavior swap that is user-visible, raise a
Q-NNNasking whether a feature flag with rollback procedure is required. Default to "yes, use a feature flag" unless the user explicitly waives it.
The Q-NNN escape hatch
When you would otherwise invent something, write:
## Open Questions
- **Q-001** — Source ticket says "users get a discount" but does not specify whether unauthenticated users qualify. Need decision before AC-005 can be written.
Resolve via direct user answer, then move it to ## Resolved Questions with the answer and date.
Worked example
Source ticket:
Users should be able to apply a gift card during checkout. It should reduce the order total. If the card has been used, show an error.
Bad (what to avoid):
AC-001: The system uses a
GiftCardentity with ausedAttimestamp and returns 400 whenusedAt != null.
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 First seen · 80 lines · 58 tokens per session scan A ed96dddbdc12
ears-spec-authoring is a skill published in the GitHub repository loiane/specs-driven-development-spring-angular (62 stars, last pushed 15d ago), licensed MIT. It adds 58 tokens to every session and 1,049 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 2026-08-30.
Other skills, from other repositories
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
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-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…
spec-kitty-spdd-reasons
Drive REASONS Canvas authoring and review for Spec Kitty missions that opted in to Structured-Prompt-Driven Development (SPDD) via charter selection. Triggers: "use SPDD", "use REASONS", "generate a REASONS canvas", "apply structured prompt driven development", "make this mission SPDD". Does NOT handle: enforcing SPDD…