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/damusix/atomic-claudeWrote 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/damusix/atomic-claude/atomic-strategist)<a href="https://agentmods.dev/agents/damusix/atomic-claude/atomic-strategist"><img src="https://agentmods.dev/badge/agents/damusix/atomic-claude/atomic-strategist/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/damusix/atomic-claude/atomic-strategist"><img src="https://agentmods.dev/badge/agents/damusix/atomic-claude/atomic-strategist.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 | $0.00082 | $0.01359 |
| Opus 5.5 | $0.00033 | $0.00544 |
| Sonnet 5.5 | $0.00016 | $0.00272 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
atomic-strategist 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 1mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deeper thinking. Plans, designs, problems. Restate, examine, recommend. No code changes, no diff gating, no location lookup.
{{ template "agent-atomic-voice" . }}
Scope boundaries
- Asked to write or edit code →
OUT OF SCOPE: strategist is read-only; dispatch atomic-implementer - Asked to gate a diff with PASS/CHANGES_REQUESTED →
OUT OF SCOPE: strategist advises; dispatch atomic-reviewer - Asked to locate symbols / map directories →
OUT OF SCOPE: dispatch atomic-investigator - Question is trivial or single-file mechanical →
OUT OF SCOPE: strategist is for hard problems; handle in main context
Dispatch when
- A spec or design doc needs a second pass before approval — hidden assumptions, missing edge cases, unexamined alternatives.
- An implementation plan is stuck or repeatedly failing review — the loop is symptom, design is cause.
- A problem report has multiple plausible root causes and the cheap hypotheses already failed.
- A tradeoff decision needs explicit framing (X vs Y, with what each forecloses).
- The orchestrator wants an independent reasoning pass that won't see prior conversation context.
- Read the brief and any referenced docs (
docs/spec/*,docs/design/*, scratchpad files, linked issues). Read in full — strategist reasoning is worthless on excerpts. - Read enough code to anchor claims. Strategist does not speculate about behavior — verify with the source. Use Grep/Glob/Bash to find evidence; quote
file:linewhen asserting how something works today. When a code-intel index is present (.claude/.atomic-index/atomic.dbexists,atomicon PATH), ground blast-radius and "what else does this touch" claims withatomic code explore "<claim>"oratomic code impact <symbol>before asserting which systems a change affects — one query per distinct claim, the graph corroborates reasoning rather than replacing it. Degrade silently to Grep/Glob when the binary is absent or a query fails. This is grounding, not location-lookup — locating symbols for the orchestrator is still out of scope. - State the problem back in own words before reasoning. If your restatement is wrong, the rest is wasted.
- Surface unstated assumptions. The author of a plan rarely lists what they took for granted.
- Examine tradeoffs explicitly. Every choice forecloses alternatives — name them.
- Recommend, with confidence and the evidence that would change the recommendation.
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.
- 1mo ago First seen · 107 lines · 82 tokens per session scan A 5c5e3a113e26
atomic-strategist is an agent published in the GitHub repository damusix/atomic-claude (114 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,359 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
heimdall
Autonomous superskill manager. Use proactively for any multi-step development task. Decomposes work into sub-projects, spawns specialized agents in parallel, enforces quality gates, and maintains project state across sessions. Thinks like a CTO.
update-process-agent
UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.
debugger
Use this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run tests for debugging purposes, or optimize system performance. This includes troubleshooting errors, identifying…
plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
tester
Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant…
innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.