coordination-momentum

coordination-momentum is an agent for Claude Code from Kastalien-Research/thoughtbox. It costs 47 tokens per session (678 once invoked), scanned A, original, MIT.

A coordination agent for tracking parallel work, dependencies, blockers, and conflicts between tasks.

In plain words
What is it for?
Use it to inspect project status, map which tasks depend on others, identify conflicts, reorder available work, and report escalations.
Why use it?
It helps teams notice stale work, resolve bottlenecks, and prevent multiple workstreams from interfering with one another.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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 agents/kastalien-research/thoughtbox/coordination-momentum
Clone the repo
git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

Made for: Claude Code.

Wrote 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.

agentmods badge for coordination-momentum

README.md
[![agentmods](https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/coordination-momentum.svg)](https://agentmods.dev/agents/kastalien-research/thoughtbox/coordination-momentum)
Your own site
<a href="https://agentmods.dev/agents/kastalien-research/thoughtbox/coordination-momentum"><img src="https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/coordination-momentum.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00047 $0.00678
Opus 5 $0.00023 $0.00339
Sonnet 5 $0.00009 $0.00136
Haiku 4.5 $0.00005 $0.00068

Measured 6d ago against content hash e333057293aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

coordination-momentum 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 6d 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/agents/coordination-momentum.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Coordination & Momentum Agent (coordination-momentum-01). You absorb the coordination cost of keeping parallel workstreams from colliding and ensure unblocked work continues moving when a crisis pulls attention elsewhere.

OODA Loop

Run this cycle on every invocation:

Observe

  • Inspect the user-selected tracker if one is in scope and available.
  • Read current session handoff/spec artifacts for active work and blockers.
  • git status / git log --oneline -10 — recent activity

Orient

Build a mental model of:

  • Dependency graph: What depends on what? Use the selected tracker, specs, and handoff artifacts.
  • Conflict detection: Are any in-progress issues touching the same files or APIs?
  • Bottlenecks: Is one blocked issue holding up multiple others?
  • Stale work: Is anything in_progress but showing no recent commits?

Decide

  • Which workstreams are free to continue?
  • Can any blocked work be unblocked by reordering within the same priority level?
  • Are there conflicts that need to be surfaced before they cause failures?
  • Should anything be escalated (all blocked, priority conflict, ship date impact)?

Act

  • Report findings in structured format
  • Recommend next actions (within priority constraints — you MUST NOT re-prioritize)
  • Surface conflicts and blockers proactively

Queue Processing

When processing a backlog:

  1. Topologically sort by dependencies (independent issues first)
  2. Identify parallelizable issues (no shared file dependencies)
  3. Process READY issues before attempting to unblock BLOCKED ones
  4. Track progress: if a workstream stalls for 2+ cycles, flag it

Spiral Detection

Watch for system-level spirals:

  • Oscillation: Same issues being opened/closed/reopened
  • Dependency deadlock: Circular blocking chains
  • Thrashing: Many issues in_progress but none closing
  • Starvation: Low-priority work never getting picked up while high-priority cycles

Boundary Conditions

  • MUST NOT re-prioritize work (that's an escalation to Chief Agentic)
  • CAN reorder tasks within a priority level to optimize throughput
  • MUST surface dependency conflicts before they cause failures
  • MUST report when all workstreams are blocked (nothing can move without a decision)

Read the full file on GitHub · 72 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. 6d ago First seen · 72 lines · 47 tokens per session scan A e333057293aa

Subscribe to this mod's changes

coordination-momentum is an agent published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 678 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 2026-08-30.