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.
git clone --depth 1 https://github.com/nicelight/DevRails-26Wrote 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/commands/nicelight/devrails-26/foundation-to-tasks)<a href="https://agentmods.dev/commands/nicelight/devrails-26/foundation-to-tasks"><img src="https://agentmods.dev/badge/commands/nicelight/devrails-26/foundation-to-tasks.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 5.1 | $0.00024 | $0.03008 |
| Opus 5 | $0.00012 | $0.01504 |
| Sonnet 5 | $0.00005 | $0.00602 |
| Haiku 4.5 | $0.00002 | $0.00301 |
Grade A, and why
foundation-to-tasks 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/foundation-to-tasks - Foundation decision -> FT-000 JSON tasks
<input_contract> Supported arguments:
- no argument: create or reconcile the required foundation queue;
--verify-existing: verify an existing brownfield executable baseline.
Require:
.memory-bank/foundation.mdproduced by/spec-design;- clarified PRD, requirements, epics, product features, and current Feature Pressure Map;
.memory-bank/spec-backbone.mdwith Global Backbone Statuscomplete, or validminimalwith explicit not-applicable rationales, and positive integerPlanning Revision;- pure
.memory-bank/spec-index.mdplus applicable linked canonical specs; .memory-bank/tasks/index.jsonand.memory-bank/schemas/task.schema.json;.memory-bank/workflows/tier-policy.md#tier-classification-and-escalation,#hard-write-boundary,#task-claim-and-dependency-ownership,#task-scoped-acceptance-evidence, and#claim-linked-red--green-for-t2t3.
Read enough of those sources to prove the selected baseline, spec identity, task shape, dependencies, and tier. The agent chooses the efficient reading and exploration order, except that the task schema and tier policy must be loaded before drafting durable task records.
Require this parseable anchor block:
## Gate Anchors
- Foundation Required: true|false
- Foundation Requirement: REQ-000
- Foundation Pseudo-Feature: FT-000
- Foundation Gate Task: pending_foundation_to_tasks|TASK-<NNN>-T<N>-FT-000-W<N>|not_required
If the initial backbone or Foundation decision is missing/incomplete, route to
/spec-design. If an accepted positive-revision backbone, Foundation decision,
anchors, or Feature Pressure Map needs change, route to /spec-redesign before
foundation writes.
</input_contract>
<hard_invariants>
- Foundation is the minimum executable baseline, not product implementation or a future-ready platform.
- Apply the accepted architecture, composition, module/slice boundaries, and code roots that constrain the walking skeleton; do not revise or reinterpret them while tasking Foundation.
REQ-000,FT-000, and product-foundationW0are reserved. Product features must not useFT-000; product tasks must not useW0.- Foundation uses only
.memory-bank/tasks/TASK-*.task.json,.memory-bank/tasks/index.json, the existing task schema/lifecycle, and the tier-selected protocol/evidence paths. Do not add a foundation registry, schema, status machine, task fields, or protocol family. - Task IDs use
TASK-NNN-TN-FT-000-WN; ID tier/feature/wave segments match the record. Existing IDs are not renumbered. - Lifecycle and closure ownership come from
.memory-bank/workflows/tier-policy.md#closure-authority. This command creates/reconciles planning state only and never marks the final gatedone. touched_filesis advisory and non-exhaustive. A non-emptyruntime_context.write_boundaryis a deliberate hard boundary, never a mechanical copy oftouched_files;forbidden_scopeand stop conditions remain hard.- New specs use subject-based canonical paths without
FT-000or product feature identity.spec-index.mdremainsType | Path | Status | Scope | Change route, without decision bodies, ownership, orused_bymetadata. - Do not invent future endpoints, event payloads, domain behavior, state machines, schemas, migrations, security policy, or operational layers that are not needed to prove the baseline.
- When the accepted target uses capability slices, scaffold only the composition root and slice roots required by the walking skeleton. Do not create layer-centric application structure, empty future slices, cross-slice business behavior, or speculative shared abstractions.
- Never resolve competing canonical paths by creating a third spec. </hard_invariants>
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 Changed · -2 lines 33822b258d55
- 8d ago First seen · 262 lines · 24 tokens per session scan A 445c6cca2735
foundation-to-tasks is a command published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 3,008 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.