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/loiane/specs-driven-development-spring-angular/ears-spec-authoringnpx 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.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 | $0.00058 | $0.01049 |
| Opus 5 | $0.00029 | $0.00524 |
| Sonnet 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 4d 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.
- 4d 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 (58 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,049 once invoked, about $0.0003 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 2026-08-30.
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-implement-review
Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state transitions, rejection cycles, arbiter escalation, and dependency-aware sequencing across all 13 supported coding agents. Triggers: "implement and review WPs", "run the implement-review loop"…
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-program-orchestrate
Orchestrate a multi-repo, multi-mission Spec Kitty program end-to-end: run specify → plan → tasks → implement → review → merge → mission-review → post-merge fixes across several repositories in a defined dependency order, using background sub-agents for parallel work and a pulse-heartbeat safety net for long…
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-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…