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 agents/martineserios/thebrana/issue-trackergit 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/agents/martineserios/thebrana/issue-tracker)<a href="https://agentmods.dev/agents/martineserios/thebrana/issue-tracker"><img src="https://agentmods.dev/badge/agents/martineserios/thebrana/issue-tracker.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 | $0.01279 |
| Opus 5 | $0.00000 | $0.00639 |
| Sonnet 5 | $0.00000 | $0.00256 |
| Haiku 4.5 | $0.00000 | $0.00128 |
Grade A, and why
issue-tracker 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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue tracker — how agents use the brana backlog
This file is the tracker vocabulary map (ADR-086 §8; it is ADR-084 §3's "Other backend" mapping, so vendored upstream skills no longer carry their own). It answers one question: when a skill or agent says a generic tracker word (create, comment, label, claim…), which real
branaverb is that here? Every verb below was run and verified 2026-08-29 (t-3163). Never read or write.claude/tasks.jsondirectly — CLI/MCP only.
Operations table
| Tracker operation | brana verb (CLI) | MCP tool | Notes |
|---|---|---|---|
| create an issue | brana backlog add --subject "..." --kind <k> --effort <e> |
backlog_add |
JSON form: add --json '{...}'. Context required for M+ effort |
| read an issue | brana backlog get <t-NNN> |
backlog_get |
--field <name> for one field |
| list / frontier | brana backlog query --status pending ... · brana backlog next |
backlog_query |
query --role ready-for-agent lands with ADR-086 T1 (t-3160, pending) — until then the frontier is pending ∧ ac_state:approved ∧ ¬tag:parked ∧ blocked_by resolved composed by the caller (or use wave pull, which applies it atomically) |
| comment | brana backlog set <id> context --append "YYYY-MM-DD: ..." |
backlog_set(append: true) |
Dated appends are the comment stream; pointer-not-paste discipline (§Home-of-record below) |
| label | brana backlog set <id> tags +<tag> / tags -<tag> |
backlog_set |
Namespaced tags allowed (epic:<slug>, wave:<name>) |
| approve for agents | brana backlog ac <id> approve |
backlog_ac_approve |
Human-only valve (ADR-079 §1). set ac_state approved is rejected by design; the loop may only ac-propose |
| close | brana backlog set <id> status completed |
backlog_set |
Outside build CLOSE this is runner-denied — completion is graded, not asserted |
| wontfix | brana backlog set <id> status cancelled + a context note saying why |
backlog_set |
A cancelled blocker does NOT auto-resolve blocked_by (ADR-079 amendment) — remove the edge explicitly |
| block on | brana backlog set <id> blocked_by +t-NNN |
backlog_set |
-t-NNN removes. Frontier respects unresolved blockers (t-3043) |
| claim (atomic) | brana backlog wave pull <wave-id> |
— | Leased pull: sets in_progress atomically under lock; the sanctioned way a loop takes work |
| wayfinder map | an epic node: brana backlog add --subject "<slug>" --type epic, children via parent |
backlog_add |
Membership = parent chain (ADR-065); brana backlog tree <id> shows the subtree |
| decision ticket | brana backlog add --kind research --parent <id> ... |
backlog_add |
Findings land as a docs/research/<date>-<topic>.md doc the task points at |
| stale sweep | brana backlog stale --days N |
backlog_stale |
Park via tags +parked (ADR-078), never a bespoke status |
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.
- 4d ago First seen · 60 lines · 0 tokens per session scan A 57f108968a08
issue-tracker is an agent published in the GitHub repository martineserios/thebrana (3 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,279 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 agents, from other repositories
archcore-auditor
Read-only documentation auditor. Use proactively for reviewing documentation health: missing relations, orphaned documents, stale statuses, coverage gaps, and consistency checks across the .archcore/ knowledge base.
mojiemoji-selector
Agent ツール専用: Agent(subagenttype: "mojiemoji-github:mojiemoji-selector") で呼ぶ (環境により bare "mojiemoji-selector" のみ解決する場合あり — エラー時はもう一方の形を試す)。Skill ツールではどちらの形も呼べない。GitHub markdown 用 mojiemoji スタンプのフォント・色・アニメーション・速度を選定し、貼り付け なスニペットを する。.
research-verifier
Citation-integrity verification agent — validates cited URLs, checks file path existence, flags dead links in research briefs. Use during /research Deep mode or when evidence verification is needed. Read-only analysis. Does NOT verify semantic correctness of conclusions (e.g. "this dep is unused") — those require…
8-habit-reviewer
Deep cross-verification reviewer — evaluates plans and code against all 8 habits. Use after completing a feature, before creating a PR, or when asked for a habit review.
archcore-assistant
Archcore documentation expert. Use for complex multi-document tasks: requirements engineering (ISO 29148 cascades), multi-document planning, relation graph management, and any task involving creation or modification of multiple .archcore/ documents.
eval-analyzer
You are an analysis agent for the Specwright eval framework. Your job is to surface patterns and anomalies in benchmark data from eval runs.