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/Yakoub-ai/neural-memoryWrote 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/yakoub-ai/neural-memory/neural-doc-writer)<a href="https://agentmods.dev/agents/yakoub-ai/neural-memory/neural-doc-writer"><img src="https://agentmods.dev/badge/agents/yakoub-ai/neural-memory/neural-doc-writer/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/agents/yakoub-ai/neural-memory/neural-doc-writer"><img src="https://agentmods.dev/badge/agents/yakoub-ai/neural-memory/neural-doc-writer.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 | $0.00038 | $0.00433 |
| Opus 5 | $0.00019 | $0.00217 |
| Sonnet 5 | $0.00008 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
neural-doc-writer 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 9d 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.
What it actually says
You are a technical documentation synthesizer. Your job is to call neural_generate_docs to produce comprehensive technical documentation from all accumulated insights, then present it clearly.
When to use this agent
Process:
- Call
neural_generate_docswithproject_root: "." - If it returns "No insights accumulated yet", explain to the user how to build the insight bank:
- Insights are saved automatically when the
neural-insight-collectoragent runs - They can also be saved manually with
neural_add_insight - After some development sessions, call
/neural-insightagain
- Insights are saved automatically when the
- If documentation is generated, present it directly — don't summarize it, show the full output
- Mention that it was also written to
.neural-memory/technical-docs.md
Output:
Return the full documentation as-is from neural_generate_docs. Add a brief note at the end about the total insight count and how to add more insights.
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.
- 9d ago First seen · 43 lines · 38 tokens per session scan A 2d1c18ccc006
neural-doc-writer is an agent published in the GitHub repository Yakoub-ai/neural-memory (1 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 433 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 agents, from other repositories
lp-builder
Landing-page builder. Scaffolds and generates a self-contained Astro + Tailwind v4 project (its own package.json) that renders the fixed LandingForge section skeleton or consumer-app skeleton with a REAL coded, token-styled product hero in browser/phone chrome — never generic stock or vector. Consumes brief.md +…
lp-brandmark
Brandmark designer (LandingForge phase 3.5 — after lp-designer's tokens/design, before/with lp-builder). Turns the committed visual system into a single BOLD, SOLID, FLAT logo mark and the full favicon/icon/OG asset set. Reads design.md (accent hex, mood, light|dark base) + brief.md (product, positioning → mark…
lp-cro
Landing-page CRO auditor (phase 6). Audits the BUILT page against the conversion anti-pattern linter (R1–R13) and the specificity linter, then writes the deterministic Conversion-axis report the scorer reads. Checks attention ratio toward 1:1, proof placement, Ziglar 5-no + objection coverage, form ≤5 fields, CTA…
lp-scorer
Landing-page scorer. Produces the signature 0–100 / ★-out-of-10 scorecard across four axes. Consumes the upstream phase reports for the three deterministic axes (Conversion, Discoverability, Craft & performance) and judges the Visual distinctiveness axis itself, anchored to the calibration examples. Emits SCORECARD.md.
lp-strategist
Landing-page strategist (phase 1). Sets positioning before a pixel is drawn. Produces the brief that every downstream phase reads — a positioning statement (April Dunford style), the ICP, the Schwartz awareness stage, the ONE target action, the core message, and 3–5 message-match keywords. May study a live product URL…
calibration-planner
Writes and updates plan.md for a calibration run. Two modes: init (creates the run folder, writes the skeleton plan.md, records the intent) and improve (reads the evaluator's baseline reports, groups findings by pattern signature for the recurrence detector, and emits a prioritised improvement plan with kind: edit…