sitrep CLAUDE.md

Project instructions for Sitrep, an open-source framework that keeps operations, costs, decisions, and continuity in markdown files inside a software repository.

In plain words
What is it for?
Use them when changing the Sitrep project so scope, technical specifications, decisions, and session rules stay consistent.
Why use it?
They tell an AI coding assistant which sources of truth to trust and how to manage work across stories, branches, tickets, specifications, and decision records.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/viitorohit/sitrep/claude-md
Clone the repo
git clone --depth 1 https://github.com/viitorohit/sitrep
Per session 2,024 This file is loaded in full into every session.
When invoked 2,024 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02024 $0.02024
Opus 5 $0.01012 $0.01012
Sonnet 5 $0.00405 $0.00405
Haiku 4.5 $0.00202 $0.00202

Measured 3d ago against content hash a5e0c33e0ae4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sitrep CLAUDE.md 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.

CLAUDE.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — sitrep Project

Project Overview

sitrep is an open-source AI-native project operations framework — the operations, cost, and continuity layer for AI-assisted development. It lives inside developer repos as markdown files that AI coding assistants read and update. It sits BESIDE planning tools (Jira, OpenSpec, Spec Kit), it does not replace them.

GitHub: github.com/viitorohit/sitrep · Domain: getsitrep.dev · License: MIT Shipped: v0.3.0 "Sharper & Self-Sufficient" (npm + GitHub release, 2026-07-08) · In development: v0.4.0 "Cost-to-Outcome & Beside"

Sources of Truth — Priority Order

  1. Jira project GETSITREP — canonical for scope, status, build order. Atlassian MCP is connected — fetch live rather than asking the session owner to paste.
  2. This repo, docs/specs/ — canonical for technical specs (command canon, adapter contract, cost schema), as they're authored. Confluence is a mirror of this, not the source (flipped 2026-07-03 — see ADR index below; specs not yet migrated are still Confluence-only until their owning Story authors the docs/specs/ version as part of its acceptance criteria).
  3. docs/adr/ — canonical for why a decision was made. Immutable once Accepted; only ever superseded, never edited. Read the relevant ADR instead of asking "why" — don't re-litigate a decision that already has one.
  4. This file — durable operating rules only (governance, hard laws, pointers). No decision rationale lives here anymore — that's what ADRs are for. No file-tree snapshot either (previous versions drifted twice) — audit the actual tree yourself at session start (ls, git status).
  5. sitrep/ dogfood files — reconciled and actively maintained (STATUS_REPORT.md/PROJECT_PLAN.md/.sitrep-data.json via session-end, dashboard.html folded into the same commit per ADR-0007). Still worth a quick git log/Jira cross-check at session start — this project has hit real drift before when a session skipped session-end (see GETSITREP-54, and the Session 9 close-out incident in sitrep/STATUS_REPORT.md's own log).

Read the full file on GitHub · 76 lines

Changes

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.

  1. 3d ago First seen · 76 lines · 2,024 tokens per session scan A a5e0c33e0ae4

Subscribe to this mod's changes

sitrep CLAUDE.md is an instructions file published in the GitHub repository viitorohit/sitrep (19 stars, last pushed 1mo ago), licensed MIT. It adds 2,024 tokens to every session, about $0.0101 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 2026-08-30.

Related

Other instructions, from other repositories