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/axiomantic/spellbookWrote 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/commands/axiomantic/spellbook/estimate-buffer)<a href="https://agentmods.dev/commands/axiomantic/spellbook/estimate-buffer"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/estimate-buffer/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/commands/axiomantic/spellbook/estimate-buffer"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/estimate-buffer.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 | $0.00025 | $0.02520 |
| Opus 5 | $0.00013 | $0.01260 |
| Sonnet 5 | $0.00005 | $0.00504 |
| Haiku 4.5 | $0.00003 | $0.00252 |
Grade A, and why
estimate-buffer 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 5d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Estimate Buffer (Phases 6-7)
Arbitrary fudge factors (e.g. "multiply by 1.5 to be safe") are FORBIDDEN. The buffer comes from PERT sigma, not from gut feel.
N-engineer scaling is NOT linear. Apply Brooks's Law constants explicitly.
Invariant Principles
- Buffer is a distribution, not a number: The output is E_total plus sigma_total feeding 80/90/95% bands; collapsing to "the estimate is X hours" skips PERT entirely.
- Sigma replaces fudge factors: All buffer comes from PERT three-point sigma; arbitrary multipliers ("times 1.5 to be safe") are forbidden.
- Variance adds, deviations do not: Aggregate as sigma_total = sqrt(sum of per-ticket variances), never sum of per-ticket sigmas.
- Brooks's Law bounds the second engineer: N=2 calendar uses explicit pair (15%) and parallel (10%) overhead constants, never linear calendar/N compression.
- Roundtable gates the handoff: Skeptic, Pragmatist, and Optimist challenge the numbers in parallel before the report; any pause/revise verdict goes to the user before proceeding.
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.
- 5d ago First seen · 225 lines · 25 tokens per session scan A 185ec2e5a7fb
estimate-buffer is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 2,520 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 2026-09-03.
Other commands, from other repositories
report-issue-with-atomic
Open an issue against the atomic-claude repo itself (bugs/feature requests with the installed config, not the user's current project).
report-issue
Open a atomic GitHub issue via gh. Bug report or feature request — auto-detect from user's description.
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
status
Show current Heimdall state — project phase, active agents, quality gates, conflicts.
beads-loop
Execute beads iteratively until all tasks complete.
beads-swarm
Execute beads with parallel agent swarm (dependency-aware).