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/martineserios/thebrana/reference.specgit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/reference.spec)<a href="https://agentmods.dev/commands/martineserios/thebrana/reference.spec"><img src="https://agentmods.dev/badge/commands/martineserios/thebrana/reference.spec.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00256 |
| Opus 5 | $0.00000 | $0.00128 |
| Sonnet 5 | $0.00000 | $0.00051 |
| Haiku 4.5 | $0.00000 | $0.00026 |
Grade A, and why
reference.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 3d 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
reference.rs — generator spec (skill frontmatter reference)
Task: t-1341 Related: docs/architecture/testing-validation.md (canonical enum source)
Scope
The generated docs/reference/skills.md must surface the legal values for
the group, growth_stage, and status keys in skill SKILL.md frontmatter.
Today those enums live only in docs/architecture/testing-validation.md,
which users discovering "what's a valid group?" rarely think to check.
Contract
generate_skills emits a "Skill Frontmatter Reference" section between the
top-level summary and the per-skill Index. The section is a static block
keyed off SKILL_FRONTMATTER_REFERENCE so the canonical enum list lives in
one place; if testing-validation.md adds a new value, this constant must be
updated in the same change.
The section must include:
- A
groupenum table mirroringtesting-validation.mdCheck D - A
growth_stageenum table - A
statusenum table
Out of scope
- Validating frontmatter values at generation time (that's validate.sh's job)
- Generating the constant from
testing-validation.mdat runtime
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.
- 3d ago First seen · 30 lines · 0 tokens per session scan A 2360936b5557
reference.spec is a command published in the GitHub repository martineserios/thebrana (3 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 256 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 2026-08-31.
Other commands, from other repositories
build
Build a feature using the adversarial review loop. Default tier: parent works end-to-end, zero subagent spawns. --strict tier adds critic + external review.
check-pr
Check the current branch's PR for external review feedback, fix errors and warnings, run a final external review, and push.
backlog-status
Display a live backlog status dashboard — active tasks table with PR state and branch-to-test. Optional flag: --qa also generates a QA test guide for all Ready-for-Review tasks.
help
Show comprehensive help guide for the agent team system.
review
Run the adversarial critic against existing code. Default: parent reviews inline, zero subagent spawns. --strict: critic subagent + external review.
techstack-refresh
View, create, or update TECHSTACK.md for the current project. Runs the Technology Discovery Protocol to detect the project's stack from source files, package manifests, and CI/CD config. Safe to run at any time — existing user-added content is always preserved. Use --force to bypass the 72-hour freshness check and…