prime

A command for preparing an AI coding session to work on the forge framework by loading its documentation, recent changes, version information, roadmap, and project boundaries.

In plain words
What is it for?
Use it at the beginning of forge framework work so the agent can review the repository's current guidance and status before making changes.
Why use it?
It reduces the setup and context-gathering needed at the start of each development session and checks that you are in the correct repository.

Command

Part of the forge plugin — 7 commands shipped together

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 commands/ktoulgaridis/forge/prime
Clone the repo
git clone --depth 1 https://github.com/ktoulgaridis/forge

Or install forge, the plugin that ships this one along with the rest of its 7 commands.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,426 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 $0.00034 $0.01426
Opus 5 $0.00017 $0.00713
Sonnet 5 $0.00007 $0.00285
Haiku 4.5 $0.00003 $0.00143

Measured 3d ago against content hash 9a2e3f613e49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prime 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.

commands/prime.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge:prime — Calibrate this session for forge work

The contributor analog to the /prime <role> skill that forge stamps into projects. Reads everything a fresh session needs to pick up forge framework development without prompting from the human.

Invocation

/forge:prime

No arguments. Run from inside the forge repo (~/Work/forge or wherever cloned).

What this command does

Run these steps in order. The agent reading this command performs each step itself; this is a structured prompt, not auto-executed automation.

1. Verify location

test -f .claude-plugin/plugin.json || { echo "not in forge repo"; exit 1; }

If not in forge, stop and tell the user cd ~/Work/forge first.

2. Load core context

Read these in order (cite them by path when summarizing):

README.md                   Status + roadmap + scope boundaries
CONTRIBUTING.md             Conventions: commits, versioning, releases, method-vs-content
docs/METHOD.md              The principles forge stamps into projects
docs/METHODOLOGY.md         The bundle work next on the roadmap
docs/SESSIONS.md            Ephemeral-by-default lifecycle
docs/USAGE.md               Day-to-day ops of stamped projects (so you understand what forge produces)
docs/ROLES.md               Role pattern stamped into projects
docs/ADAPTERS.md            Adapter contract; how adapters compose into skills
docs/BOOTSTRAP.md           First-time setup walkthrough for stamped projects

3. Pull live state

# Current version
jq -r .version .claude-plugin/plugin.json

# Recent commits (what landed in the last few sessions)
git log --oneline -15

# Releases cut so far
gh release list --limit 5

# Working tree state (anything mid-flight?)
git status -s

# Branches (any feature branches in flight?)
git branch -v

4. Inventory shipped capabilities

Walk these dirs and note what's actually in them:

ls adapters/tracker/        # which trackers ship
ls adapters/scm/            # which SCMs
ls adapters/chat/           # which chats
ls adapters/ci/             # which CI adapters (probably empty until v0.2)
ls templates/wiki/roles/    # default roles + custom template
ls templates/wiki/_snippets # session bootstrap snippets
ls commands/                # plugin slash commands available

Read the full file on GitHub · 161 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 · 161 lines · 34 tokens per session scan A 9a2e3f613e49

Subscribe to this mod's changes

prime is a command published in the GitHub repository ktoulgaridis/forge (10 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 1,426 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 2026-08-31.