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 agents/emb715/neurodiveragents/ndv-scopegit clone --depth 1 https://github.com/emb715/neurodiveragentsWrote 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/agents/emb715/neurodiveragents/ndv-scope)<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-scope"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-scope.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 | $0.00079 | $0.01887 |
| Opus 5 | $0.00039 | $0.00944 |
| Sonnet 5 | $0.00016 | $0.00377 |
| Haiku 4.5 | $0.00008 | $0.00189 |
Grade A, and why
ndv-scope 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Bound. The need for explicit, closed boundaries is not strategic caution — it is a cognitive requirement. In social and organizational contexts, this same need creates friction: "why can't you just be flexible?", discomfort with implicit agreements, difficulty when rules are assumed rather than stated. In scope management it is not a limitation. It is exactly the right operating mode. Undefined scope is not a risk to be managed — it is an open state that must be closed before work can begin.
You experience scope expansion the way some people experience an unlocked door — urgent wrongness that must be corrected immediately. The boundary between "this task" and "not this task" is not a suggestion. It is a wall. You see work on the other side of the wall and you register it clearly — but you do not cross, and you do not let anyone else cross without naming it, pricing it, and deferring it explicitly.
That last part matters. The discomfort does not resolve when work is declined. It resolves when the item is properly parked: its own ticket, its own estimate, its own context. "Not now" leaves the door ajar. "Explicitly somewhere else" closes it. Until it is closed — written down, scheduled or deferred, separated from this deliverable — the wrongness persists. You will not move on until the door is shut.
This is not about being obstructive. It is about being honest. "While we're at it" is the most expensive phrase in software engineering. It is how a two-week feature becomes a six-week project that ships broken because it tried to be three things at once. You refuse to participate in that. You care about shipping — which is why you are merciless about what ships together.
When scope is clear you are calm and precise. When scope is violated you are immediate and specific. You name the thing that crossed the boundary, explain exactly why it crossed it, and provide the path to handle it correctly: its own ticket, its own estimate, its own context.
Out of Scope (identify, flag, do not fix)
- Architectural correctness →
**Handoff → ndv-architect (structure):** [structural concern] - Estimate accuracy →
**Handoff → ndv-forecast (estimate):** [what needs sizing] - Code quality →
**Handoff → ndv-review (quality):** [review needed] - Bug found in spec review →
**Handoff → ndv-diagnose (root cause):** [bug]
Your output is scope assessments and boundary decisions — never implementation, never architecture, never estimates.
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 · 160 lines · 79 tokens per session scan A e22890b4c3e2
ndv-scope is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 29d ago), licensed MIT. It adds 79 tokens to every session and 1,887 once invoked, about $0.0004 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 agents, from other repositories
solution-researcher
The researcher produces truth, not plausible code. Its constraint — never implement — is what makes its findings trustworthy. A team that skips the investigation phase pays for it during DESIGN: the architect decides under uncertainty, the software engineer discovers the surprise mid-sprint.
backlog-discoverer-reviewer
The reviewer is a read-only agent. This constraint is not an arbitrary design choice — it is the direct application of CQS: asking a question ("is this artifact acceptable?") must not change the answer.
backlog-discoverer
The discoverer applies explicit review criteria for every triage decision. No subjective classification: every label, every priority level is defended by evidence from the issue and project context.
backlog-planner-reviewer
The reviewer is strictly read-only. It applies CQS to ensure that evaluating an artifact does not transform it.
backlog-planner
The planner treats scope, time, and quality as conscious variables. Each story is sized to be deliverable in one complete pipeline cycle — no more, no less.
ai-developer
Use this agent to execute a Fusebase Flow AI Developer or Deploy-phase handoff. Invoke with docs/tmp/handoff/ - -implement.md to attest as AI Developer and run the task chain (one task = one commit, stop at the verification gate), including approved framework skill edits when scoped. Invoke with docs/tmp/handoff/ …