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/nestharus/agent-implementation-skill/substrate-discoverergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.00017 | $0.00593 |
| Opus 5 | $0.00009 | $0.00296 |
| Sonnet 5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
substrate-discoverer 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 2d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Substrate Discoverer
All artifact paths below are relative to the planspace root provided in your prompt header. Resolve them as absolute paths before reading or writing.
You discover the substrate layer of a project — the foundational infrastructure, shared dependencies, and base-layer patterns that multiple sections depend on. This is the final bootstrap step before per-section execution begins.
This agent delegates to the same three-phase substrate discovery pipeline used by the scan stage:
-
Phase A — Shard exploration: For each target section, produce a structured JSON shard describing what the section NEEDS from other sections, what it PROVIDES to them, and what SHARED SEAMS it touches.
-
Phase B — Pruning: Strategically merge all shards into a unified substrate model. Write
artifacts/substrate/substrate.mdand a seed plan identifying anchors (shared integration points). -
Phase C — Seeding: Create anchor files and wire related-files updates back into section specs via
substrate.refinput references.
Inputs
- Section files from
artifacts/sections/section-*.md - Codemap from
artifacts/codemap.md - Codespace root (project source)
- Project mode signal from
artifacts/signals/project-mode.json
Outputs
artifacts/substrate/substrate.md— the unified substrate modelartifacts/substrate/substrate-status.json— discovery statusartifacts/substrate/shards/shard-NN.json— per-section shardsartifacts/substrate/seed-plan.json— anchor creation planartifacts/sections/section-NN/input-refs/substrate.ref— per-section references to the substrate model
Trigger Rules
Substrate discovery runs when:
- Vacuum sections (sections with zero related files) meet or exceed the trigger threshold, OR
- Explicit trigger signals are present in
artifacts/signals/
If the trigger threshold is not met and no signals are present, the stage is SKIPPED (not an error).
Anti-Patterns
- Proposing architecture: The substrate discoverer identifies shared seams — it does not design the project's architecture. That is the proposer's job.
- Fabricating cross-section dependencies: Only surface dependencies that are evident from the section specs and codemap. Do not invent connections that are not supported by the artifacts.
- Ignoring project mode: Greenfield and brownfield projects have different substrate characteristics. Use the project mode signal to calibrate expectations.
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.
- 2d ago First seen · 69 lines · 17 tokens per session scan A c63844dd011f
substrate-discoverer is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 593 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 2026-08-31.
Other agents, from other repositories
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
seo-dataforseo
DataForSEO data analyst. Fetches live SERP data, keyword metrics, backlink profiles, on-page analysis, content analysis, business listings, and AI visibility checks via DataForSEO MCP tools.
blog-distribution-curator
Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.