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/session.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/session.spec)<a href="https://agentmods.dev/commands/martineserios/thebrana/session.spec"><img src="https://agentmods.dev/badge/commands/martineserios/thebrana/session.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 5.1 | $0.00000 | $0.00312 |
| Opus 5 | $0.00000 | $0.00156 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
session.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 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.
What it actually says
session.rs — test fixture spec
Task: t-1343 Related: tasks.spec.md (rotation contract)
Scope
Bug fix in tests, not in production behavior. The write_state /
rotate_history / read_history contract is unchanged.
Problem
Three I/O tests (test_write_archives_previous, test_history_limit,
test_rotate_drops_old_entries) used hardcoded written_at timestamps from
2026-03-31. rotate_history drops entries older than 30 days; once the wall
clock advanced past 2026-04-30 those fixture timestamps started being treated
as old, so the archived entries were dropped before the assertions ran.
Fix contract
Tests that exercise write_state (which calls rotate_history) MUST use
written_at timestamps inside the 30-day retention window. A recent_ts(days)
helper returns Utc::now() - days in RFC3339 — pass small positive offsets
to stay inside the window.
sample_state() keeps its fixed 2026-03-31 timestamp; it's the shared
fixture for render and validation tests where the literal value is asserted.
I/O tests build their state from sample_state() and overwrite written_at
with recent_ts(...).
Out of scope
- Changing
rotate_history's 30-day cutoff - Changing the
write_statearchive contract - Touching render/validate tests that depend on the fixed fixture timestamp
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 · 36 lines · 0 tokens per session scan A c5d2ed0a72bb
session.spec is a command published in the GitHub repository martineserios/thebrana (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 312 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
make
Create structured implementation plan in docs/plans/.
re-ping
설치가 정상인지 확인하는 진단 명령입니다. 파일을 읽지 않고 동의 게이트도 발동하지 않는, 가장 안전한 첫 테스트입니다.
re-report
가장 최근(또는 지정한) 분석 결과를 표준 한국어 보고서 형식으로 다시 출력합니다.
biomass-conversion-index
Show biomass conversion index statistics from your prompts.
setup
Configure cc-hud statusline in Claude Code settings.
check-canon
Check promoted canonical files against current repository observation. Usage: /lumin-repo-lens:check-canon --root [--output ] [--sources all|type-ownership,naming,topology,helper-registry].