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 madaeroblade/atlas --skill atlas-bootstrapgit clone --depth 1 https://github.com/madaeroblade/atlasWrote 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/madaeroblade/atlas/atlas-bootstrap)<a href="https://agentmods.dev/skills/madaeroblade/atlas/atlas-bootstrap"><img src="https://agentmods.dev/badge/skills/madaeroblade/atlas/atlas-bootstrap/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/madaeroblade/atlas/atlas-bootstrap"><img src="https://agentmods.dev/badge/skills/madaeroblade/atlas/atlas-bootstrap.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 | $0.00037 | $0.00654 |
| Opus 5 | $0.00018 | $0.00327 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
atlas-bootstrap 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atlas Bootstrap
Resolve Atlas
Use the Atlas root defined by the user's global Claude instructions.
Expected engine:
$ATLAS_ROOT/engine/bootstrap/
Expected profiles:
$ATLAS_ROOT/profiles/
Expected templates:
$ATLAS_ROOT/templates/
If Atlas root cannot be resolved or required files are missing, stop and report the missing path.
Execute
Read and follow, in order:
$ATLAS_ROOT/engine/bootstrap/ENGINE.md$ATLAS_ROOT/engine/bootstrap/RECONNAISSANCE.md$ATLAS_ROOT/profiles/generic/PROFILE.md
Then detect repository technologies.
Load only matching profile PROFILE.md files and their VALIDATION.md files when present.
Examples:
- Laravel →
profiles/laravel/ - Vue →
profiles/vue/ - Zend Framework 1 →
profiles/zend-framework-1/ - Swift →
profiles/swift/ - React →
profiles/react/ - React Native →
profiles/react-native/ - React Native Windows →
profiles/react-windows/
Multiple profiles may apply.
Templates
Use Atlas templates as structural guidance.
Do not blindly copy placeholders.
Generate project-specific .atlas/ artifacts from repository evidence.
Existing Atlas
If .atlas/ already exists:
- treat this as rebuild/reconciliation;
- preserve trustworthy project knowledge;
- revalidate against source;
- remove obsolete knowledge;
- do not accumulate duplicate files.
Claude project instructions
If the repository has CLAUDE.md, integrate Atlas as the project knowledge layer.
Measure CLAUDE.md in bytes before and after. It must end up smaller.
CLAUDE.md is loaded on every task in the repository, forever. It is the most
expensive place a fact can live, which is the whole reason Atlas exists.
- Move durable subsystem/project knowledge into
.atlas/, leaving a pointer, not a summary. - Do not add a "where to look" table.
GRAPH.yamlis that table, and it is loaded on demand instead of always. - Preserve project-wide operating rules — how to work here is not Atlas knowledge.
- Do not remove externally managed or generated instruction blocks.
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 · 102 lines · 37 tokens per session scan A 35289cb927cb
atlas-bootstrap is a skill published in the GitHub repository madaeroblade/atlas (2 stars, last pushed 28d ago), licensed MIT. It adds 37 tokens to every session and 654 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 skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.