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 nobrainer-tech/nobrainer-tech-skills --skill nobrainer-spec-driven-developmentgit clone --depth 1 https://github.com/nobrainer-tech/nobrainer-tech-skillsWrote 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/nobrainer-tech/nobrainer-tech-skills/nobrainer-spec-driven-development)<a href="https://agentmods.dev/skills/nobrainer-tech/nobrainer-tech-skills/nobrainer-spec-driven-development"><img src="https://agentmods.dev/badge/skills/nobrainer-tech/nobrainer-tech-skills/nobrainer-spec-driven-development/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/nobrainer-tech/nobrainer-tech-skills/nobrainer-spec-driven-development"><img src="https://agentmods.dev/badge/skills/nobrainer-tech/nobrainer-tech-skills/nobrainer-spec-driven-development.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 | $0.00046 | $0.01073 |
| Opus 5 | $0.00023 | $0.00536 |
| Sonnet 5 | $0.00009 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
nobrainer-spec-driven-development 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NoBrainer Spec-Driven Development
Use spec-driven development to freeze what must be true before deciding how to
build it. This is not subagent-driven development. Session topology is handled
by nobrainer-sessions; implementation belongs to nobrainer-build and the
project's maintained engineering workflow.
Read references/spec-template.md before writing a new specification.
Persist only when it pays
Create or update a durable spec when at least one is true:
- architecture, public behavior, data shape, external interface, or security boundary changes;
- migration, irreversible effect, expensive failure, or difficult
ROLLBACK; - several dependent components, phases, writers, or sessions share a contract;
- work may be resumed later and chat context would be unsafe;
- conflicting sources or unresolved assumptions can change acceptance.
Do not create a spec for a mechanical one-file correction whose target, expected result, verification, and rollback are already unambiguous.
Lifecycle
Use one explicit state:
DISCOVERY -> DRAFT -> REVIEW -> APPROVED -> IMPLEMENTING -> VERIFYING -> ACCEPTED
Alternative terminal states are BLOCKED and SUPERSEDED. Only the owner or
the project's designated authority can approve product, risk, or scope choices.
DISCOVERY
Read current instructions, product sources, code contracts, tests, schemas,
runtime evidence, prior decisions, and existing specs. Mark every requirement
as OBSERVED, INFERRED, RECOMMENDED, or UNKNOWN. Surface contradictions;
do not silently select the convenient source.
DRAFT
Write the smallest self-contained contract that an implementer and independent reviewer can use without reconstructing the conversation. Include:
SPEC_ID, version, status, owner, source references and assumptions;- outcome, audience, scope, exclusions and non-goals;
- functional requirements, interfaces, invariants, side effects and failures;
- security, privacy, performance, compatibility and operational constraints;
- exact write surface or component boundaries;
- task graph, dependencies and safe parallelism when execution is multi-step;
ACCEPTANCEIDs mapped to tests, verifier, build/runtime and evidence;- owner gates, stop conditions, migration, recovery and
ROLLBACK; - unresolved decisions with one owner each.
What ships with it
1 file 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.
- 5d ago Changed · +5 lines a99ce3115055
- 10d ago First seen · 114 lines · 46 tokens per session scan A b59513c0d893
nobrainer-spec-driven-development is a skill published in the GitHub repository nobrainer-tech/nobrainer-tech-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 1,073 once invoked, about $0.0002 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
multi-agent-loop
Turn the current repository into a supervised multi-agent coding loop — spawn parallel AI coding agents in isolated git worktrees with file ownership, a shared radar, and human approval gates, then run the loop (status, standup, approvals) from one place.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
goal-lock
Agent Discipline Engine — lock the goal, run PLAN→DO→VERIFY→FINALIZE→OUTPUT loop, detect success masquerading. Triggers: '/goal-lock', '/goal-lock quick', 'goal lock', 'task harness'.
collab-audit
This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to generate a 14-section AI Collaboration Audit. Behavioral analysis and feedback are bundled by design — separating them causes users to skip one, defeating…
code-autopsy
🔬 CODE AUTOPSY v7.2 "12 Questions + Quantified + Deployment Verdict + diff mode + CRITICAL hard cap + Factuality Gate".
doc-drift
Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect four kinds of issues: outdated claims, mutually contradictory…