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 agentmods add commands/onehillai/asdd/specgit clone --depth 1 https://github.com/OneHillAI/ASDDWhat 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 | $0.00012 | $0.00276 |
| Opus 5 | $0.00006 | $0.00138 |
| Sonnet 5 | $0.00002 | $0.00055 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
spec 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 2d 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
Turn the request below into a spec object for this project.
$ARGUMENTS
Fill every field ASDD's definition of ready requires: outcomes, scope (in and out), constraints
(including prior decisions), and verification (how "done" is checked). If you cannot fill one, say so
and ask the specific question rather than inventing it.
Write it where this project keeps specs. Read spec_paths: in .asdd.yml and follow it: that list is
what the intake gate matches against, so a spec written anywhere else fails the gate however good it is.
The default is docs/specs/<slug>.md.
Then check it with asdd spec-check <path>. That is the same gate the pipeline runs, so a spec that
passes here passes on the PR.
If the project already uses a spec tool (OpenSpec, Spec Kit), use its output rather than writing a
second spec beside it: run that tool, then make sure spec_paths: covers where it writes (for OpenSpec,
openspec/changes/*/specs/**/*.md). ASDD requires that a spec exists and that the change is checked
against it, not that a particular tool produced it.
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.
- 2d ago First seen · 23 lines · 12 tokens per session scan A d3734d52ea13
spec is a command published in the GitHub repository OneHillAI/ASDD (5 stars, last pushed 21d ago), licensed Apache-2.0. It adds 12 tokens to every session and 276 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 2026-08-31.
Other commands, from other repositories
MIGRATE_DESIGN
Design doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync.
diff-script
Compare an MDL script against the project's current state.
toh-help
Display all Toh Framework commands and quick usage guide.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
doctor
Run the specrails health check to validate that all prerequisites are correctly configured for this repository.
doctor
Validate, install, and update Hydraia's external dependencies (codegraph, markitdown, E2E browser binaries).