speckit.companion.before-converge

speckit.companion.before-converge is a command for Claude Code from alfredoperez/speckit-companion. It costs 23 tokens per session (490 once invoked), scanned A, original, MIT.

A lifecycle hook that records when a feature's convergence check starts in a state file used by the SpecKit Companion GUI.

In plain words
What is it for?
It helps begin tracking a converge step by checking for Python and running the repository's context-writing script.
Why use it?
It lets the GUI show that convergence is running without changing the feature's status, and repeated start events do not create duplicate records.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .specify/extensions/companion/scripts/write-context.py --step converge --kind start --by extension.

Good fit It helps begin tracking a converge step by checking for Python and running the repository's context-writing script.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/alfredoperez/speckit-companion
agentmods
npx agentmods add commands/alfredoperez/speckit-companion/speckit.companion.before-converge

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 speckit.companion.before-converge

README.md
[![agentmods](https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.before-converge/github.svg)](https://agentmods.dev/commands/alfredoperez/speckit-companion/speckit.companion.before-converge)
Your own site
<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/speckit.companion.before-converge"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.before-converge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for speckit.companion.before-converge

Your own site · 80×15
<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/speckit.companion.before-converge"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.before-converge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00023 $0.00490
Opus 5.5 $0.00009 $0.00196
Sonnet 5.5 $0.00005 $0.00098
Haiku 4.5 $0.00002 $0.00049

Measured 14d ago against content hash 22b2bcbfc874, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

speckit.companion.before-converge 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 14d 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.

apps/speckit-extension/commands/speckit.companion.before-converge.md · 42 lines

What it actually says

Capture Converge Start

Record the start of the active feature's converge run into .spec-context.json so the SpecKit Companion GUI shows converge running. This command runs as the before_converge lifecycle hook and only writes state; the convergence check itself is the core speckit.converge workflow.

Prerequisites

  • Verify Python is available by running python3 --version.
  • If python3 is not available, warn the user and skip the capture: [companion] Warning: python3 not detected; skipped .spec-context.json capture. Do not fail the host command.

Execution

Run the writer script from the repository root:

python3 .specify/extensions/companion/scripts/write-context.py --step converge --kind start --by extension

There is no --status: converge owns no status and never moves the spec's status. The start is idempotent, so a re-fired hook never records a second one.

The script resolves the active feature directory on its own, in this order: --feature-dir, SPECIFY_FEATURE_DIRECTORY env, SPECIFY_FEATURE env, .specify/feature.json, current git branch prefix.

If you already know the feature directory, pass it explicitly so resolution is unambiguous:

python3 .specify/extensions/companion/scripts/write-context.py --feature-dir specs/<NNN>-<slug> --step converge --kind start --by extension

Graceful Degradation

The script is best-effort and never fails the host command:

  • If python3 is missing, skip with the warning above.
  • If the active feature directory cannot be resolved, the script prints a warning to stderr and exits 0 without writing.
  • If the spec is already completed or archived, nothing is written.

Output

On success the script prints the path it updated and the values written, e.g. [companion] Updated specs/<NNN>-<slug>/.spec-context.json (currentStep=converge, status=unchanged, kind=start, by=extension). The write is atomic and appends to history[] without rewriting existing entries.

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. 14d ago First seen · 42 lines · 23 tokens per session scan A 22b2bcbfc874

Subscribe to this mod's changes

speckit.companion.before-converge is a command published in the GitHub repository alfredoperez/speckit-companion (99 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 490 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-02.