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 skills add martineserios/thebrana --skill sitrepgit 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/skills/martineserios/thebrana/sitrep)<a href="https://agentmods.dev/skills/martineserios/thebrana/sitrep"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/sitrep.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 | $0.00032 | $0.03968 |
| Opus 5 | $0.00016 | $0.01984 |
| Sonnet 5 | $0.00006 | $0.00794 |
| Haiku 4.5 | $0.00003 | $0.00397 |
Grade A, and why
sitrep 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sitrep — Situational Awareness
One command to answer: Where am I? What was I doing? What's left? What's next?
Filters (optional args)
Sitrep accepts optional filter args after the skill name:
| Arg | Example | Applies to |
|---|---|---|
--tag <tag> |
sitrep --tag harness-engineering |
Source 3, Next action |
--stream <stream> |
sitrep --stream roadmap |
Source 3, Next action |
--kind <kind> |
sitrep --kind feature |
Source 3, Next action |
--priority <p> |
sitrep --priority P0 |
Source 3, Next action |
Multiple filters combine with AND. When any filter is active, show a Filter: line in the output header and scope all backlog queries to the filter. The session handoff (Source 4) and git state (Source 2) are never filtered.
When to use
- After context compression (conversation truncated)
- When confused about current progress or state
- Mid-session reorientation ("wait, what was I doing?")
- After returning from a tangent or interruption
- Proactively: anytime you're unsure whether to continue, stop, or switch
ToolSearch("select:mcp__ruflo__memory_search_unified,mcp__brana__session_history")
Process
Gather from 6 sources in parallel, then synthesize into one snapshot. No writes — this is read-only.
1. CC Tasks (active skill flow)
Call TaskList
Look for:
in_progresstasks → you're mid-step in a skill flowpendingtasks with completed blockers → next step to execute- Pattern: subject format
/brana:{skill} — {STEP}reveals which skill is active
If CC Tasks exist: the active skill and current step are your primary context. If no CC Tasks: no multi-step skill is running.
2. Git state
git branch --show-current
git status --porcelain | head -10
git log --oneline -5
git stash list 2>/dev/null | head -3
git worktree list
git branch --merged main
Extract:
- Current branch → maps to task convention (
feat/t-NNN-*,fix/t-NNN-*, etc.) - Uncommitted changes → work in progress that needs committing or stashing
- Recent commits → what was just accomplished
- Stashes → forgotten work-in-progress
- Worktrees → parallel work streams from
git worktree list; cross-check each worktree's branch againstgit branch --merged main. If any worktree branch appears in the merged list, surface a warning:⚠ Worktree <path> is on a merged branch — run \git worktree remove ` to clean up.`
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 · 320 lines · 32 tokens per session scan A 743dfb95c9ae
sitrep is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 3,968 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
recall-assistant
Proactive context recovery, highlight sharing, and session linking for the recall plugin. Detects context loss, suggests /recall commands, flags findings for connected sessions, and translates natural language into recall operations. Enable with /recall config skillenabled true.
session-manager
A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.
furl
How the Furl context-compression plugin works in Claude Code and Codex — the furlcompress / furlretrieve / furlstats / furlpurge / furlsearch / furllist MCP tools, the > retrieval flow, and Claude Code's optional automatic hooks. Use when the user asks what Furl is doing, how to compress or retrieve content, why…
learn
A learning workflow that examines recent project work and records repeated patterns as reusable instincts. It uses cycle documents, Git history, changed files, and logged observations.
context-memory
Saves and searches past Claude Code sessions so context, decisions, and code persist across conversations. Use when user says 'remember this', 'save this session', 'recall', 'search past sessions', 'what did we discuss about', or 'find previous work on'. Do NOT use for general file storage, note-taking, or bookmark…
log
A phase-log command that records completed work in Markdown files, a human-readable text format, and updates an index of phases.