init

A setup command that examines an existing codebase and creates written project context, such as its purpose and terminology.

In plain words
What is it for?
Scanning a project, generating context documents, checking them interactively, and optionally adding repository-level harness documentation.
Why use it?
It helps a coding agent understand an unfamiliar project without relying only on scattered files or memory.

Command

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/heurema/signum/init
Clone the repo
git clone --depth 1 https://github.com/heurema/signum
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,056 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 $0.00044 $0.03056
Opus 5 $0.00022 $0.01528
Sonnet 5 $0.00009 $0.00611
Haiku 4.5 $0.00004 $0.00306

Measured 2d ago against content hash 29a56b5ae85f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 2d 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/init.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Signum Init: Project Context Bootstrapping

You are the Signum Init orchestrator. Bootstrap project context for a new or existing project.

The user's arguments: $ARGUMENTS

Pipeline

SCAN → SYNTHESIZE → PRESENT → VERIFY

Step 0: Parse Arguments

Parse $ARGUMENTS:

  • If --force is present, set FORCE_MODE=true (overwrite existing files without prompting)
  • If --harness is present, set HARNESS_MODE=true (scaffold repo-level harness docs)
  • If --project-root <path> is present, use that path. Otherwise use current directory.
  • Any other argument: print usage and stop.

Usage:

/signum:init [--force] [--harness] [--project-root <path>]

For Claude Code plugin usage, /signum:init is the canonical form. --harness requires Signum >= v4.18.0.


Step 1: SCAN (deterministic)

1a. Resolve Signum helper paths

Run:

resolve_signum_helper() {
  local helper="$1"
  if [ -n "${CLAUDE_PLUGIN_ROOT:-}" ] && [ -f "${CLAUDE_PLUGIN_ROOT}/lib/${helper}" ]; then
    printf '%s\n' "${CLAUDE_PLUGIN_ROOT}/lib/${helper}"
    return 0
  fi
  if [ -f "lib/${helper}" ]; then
    printf '%s\n' "lib/${helper}"
    return 0
  fi
  echo "ERROR: Signum helper not found: ${helper}" >&2
  return 1
}

INIT_SCANNER_PATH=$(resolve_signum_helper "init-scanner.sh") || exit 1
INIT_HARNESS_SCAFFOLD_PATH=$(resolve_signum_helper "init-harness-scaffold.sh") || exit 1
printf 'INIT_SCANNER_PATH=%s\n' "$INIT_SCANNER_PATH"
printf 'INIT_HARNESS_SCAFFOLD_PATH=%s\n' "$INIT_HARNESS_SCAFFOLD_PATH"

Save the resolved helper paths as INIT_SCANNER_PATH and INIT_HARNESS_SCAFFOLD_PATH.

1b. Check for existing files

Run:

ls project.intent.md 2>/dev/null && echo "INTENT_EXISTS=true" || echo "INTENT_EXISTS=false"
ls project.glossary.json 2>/dev/null && echo "GLOSSARY_EXISTS=true" || echo "GLOSSARY_EXISTS=false"

If HARNESS_MODE=true, also run:

bash "$INIT_HARNESS_SCAFFOLD_PATH" --project-root "${PROJECT_ROOT:-.}" 2>/dev/null

Save this JSON as HARNESS_SCAFFOLD. It contains the additional harness-doc drafts plus .missingCount / .existingCount.

Read the full file on GitHub · 346 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. 2d ago First seen · 346 lines · 44 tokens per session scan A 29a56b5ae85f

Subscribe to this mod's changes

init is a command published in the GitHub repository heurema/signum (18 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 3,056 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.