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/thixpin/pitwayWrote 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/thixpin/pitway/usage-add)<a href="https://agentmods.dev/commands/thixpin/pitway/usage-add"><img src="https://agentmods.dev/badge/commands/thixpin/pitway/usage-add/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/thixpin/pitway/usage-add"><img src="https://agentmods.dev/badge/commands/thixpin/pitway/usage-add.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 | $0.00000 | $0.00383 |
| Opus 5.5 | $0.00000 | $0.00153 |
| Sonnet 5.5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
usage-add 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.
What it actually says
usage-add
Role: Orchestrator
pitway usage-add <id> --category planning|qa --usage <json> [--json]
pitway usage-add <id> --reading <json> [--json]
Records measured token usage — never estimated — onto a milestone's
usage.yaml, tagged planning or qa to keep it separate from per-task
usage recorded through task-update --usage. Only call this with a real,
runtime-reported figure; if a step's usage wasn't reported, leave it out
rather than guessing a number.
--reading <json> (M047) appends one measured usage reading by role
bucket instead — for figures the runtime reports about a session rather
than about one task, such as an Orchestrator session's own readings. Shape:
{"bucket": "main|orchestrator|worker|auxiliary", "count": <int>, "semantics": "per-turn|undetermined"} plus optional dimensions
(input, output, reasoning, cache_read, cache_write), model,
provider, instance_id, and raw (the provider envelope verbatim).
Readings are stored as readings — two calls are two entries, never a sum —
and --reading cannot be combined with --category. Never record a total,
a percentage, a figure split across tasks, or anything taken from Codex's
command-output original_token_count; those are refused or simply have no
field (docs/evidence/M042/synthesis.md, section 9).
See ../protocol-driver.md. Run pitway usage-add --help for flags.
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 Changed · +14 lines 4ddb25388885
- 1mo ago First seen · 21 lines · 0 tokens per session scan A 9a6b60b781dc
usage-add is a command published in the GitHub repository thixpin/pitway (20 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 383 tokens. 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 commands, from other repositories
run
A command for implementing written software requirements using domain-driven design (DDD) and test-driven development (TDD). DDD structures code around the business domain, while TDD starts with tests before implementation.
implement
Execute all implementation tasks from tasks.md with test-driven development, parallel batching, and atomic commits.
tasks
Generate TDD task breakdown from plan.md with test-first sequencing and mockup-first mode (--ui-first).
debug
Systematic root-cause investigation, then fix with TDD — never proposes a fix before finding the cause; resumable diagnosis + regression test in .orc/ state. Workspace-aware. For a quick one-off look without session state, prefer the bundled /debug.
desglosar
Dividir un blueprint técnico en tareas con TDD (RED→GREEN) y marcadores de paralelismo.
validar-spec
Validar la calidad y completitud de una especificación antes de planificar. Usa cuando el usuario dice "validar spec", "validate spec", "spec quality", "validar specs", "spec completeness", "checar specs", "check spec quality", "IEEE 29148", "spec verification". Valida que la spec esté completa y lista para…