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 rohingosling/claude-skills --skill ascii-memory-mapgit clone --depth 1 https://github.com/rohingosling/claude-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/rohingosling/claude-skills/ascii-memory-map)<a href="https://agentmods.dev/skills/rohingosling/claude-skills/ascii-memory-map"><img src="https://agentmods.dev/badge/skills/rohingosling/claude-skills/ascii-memory-map/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/rohingosling/claude-skills/ascii-memory-map"><img src="https://agentmods.dev/badge/skills/rohingosling/claude-skills/ascii-memory-map.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 | $0.00127 | $0.02075 |
| Opus 5.5 | $0.00051 | $0.00830 |
| Sonnet 5.5 | $0.00025 | $0.00415 |
| Haiku 4.5 | $0.00013 | $0.00208 |
Grade A, and why
ascii-memory-map 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 2mo 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Render an ASCII memory map using the Python script at ${CLAUDE_SKILL_DIR}/scripts/render_ascii_memory_map.py.
Author the map as JSON (the data), choose presentation flags (the rendering), run the script, and paste its output into a fenced code block. Let the script do all box drawing, alignment, address formatting, and height scaling — do not hand-draw memory maps.
Positioning rules (the text-placement taxonomy)
Every piece of text has exactly one home, decided by what it refers to:
| Class | What it is | Where it goes |
|---|---|---|
| Address | A hex/decimal boundary coordinate | Left gutter, on the divider that opens the block (its low-address edge) |
| Label | The block's short name | Inside the box, first body row |
| Description | Optional elaboration (extent, contents) | Inside the box, further body rows |
| Comment / note | Extrinsic annotation — register writes, bit patterns, caveats, consequences | Right of the box, anchored to the first body row with an arrow; continuations align beneath, no arrow |
Decisive test: text that names or describes the contents of a span is intrinsic → goes inside (label/description); text that says something about the span (a value, a constraint, a cross-reference) is extrinsic → goes outside (comment). A bare boundary coordinate goes in the gutter. Divider and border lines carry only the address — never a label or a comment. The renderer enforces all of this.
Instructions
-
Construct a JSON object describing the memory map (schema below). Store addresses as numeric/hex strings — the renderer formats them for display, so the same data can be shown as
$0400,0x0400,0400h,0040:0000, or01024by changing one flag. -
Write the JSON to a temporary file in the current project's working directory (e.g.
memmap.json). -
Run the renderer (use
python3on macOS/Linux,pythonon Windows):python3 "${CLAUDE_SKILL_DIR}/scripts/render_ascii_memory_map.py" memmap.json [flags]Defaults can also be set inside the JSON in a
"render": { ... }object; CLI flags override the JSON, which overrides the built-in defaults.
What ships with it
2 files 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.
- 2mo ago First seen · 134 lines · 127 tokens per session scan A 2059db18d1d9
ascii-memory-map is a skill published in the GitHub repository rohingosling/claude-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 2,075 once invoked, about $0.0005 per session on Opus 5.5. 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
run-memory
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run for the next one. Loaded by those playbooks; not for direct…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain — personal notes go there, not here. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/)…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
claude-md-updater
Scans the session for durable lessons and workflows, then proposes scoped project instruction updates. Use for save this lesson or add to context.