commission-programme

commission-programme is a skill for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 37 tokens per session (901 once invoked), scanned A, original, MIT.

A setup command for putting a project into the Programme software-development process, intended for teams with formal specifications and phase reviews.

In plain words
What is it for?
It helps configure the Programme bundle for production or enterprise use in a multi-team project.
Why use it?
It gives projects a defined development structure when traceability and review across stages matter.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sdlc-programme plugin — 5 skills shipped together

Good fit It helps configure the Programme bundle for production or enterprise use in a multi-team project.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add SteveGJones/ai-first-sdlc-practices
Claude Code
/plugin install sdlc-programme

Made for: Claude Code.

Or install sdlc-programme, the plugin that ships this one along with the rest of its 5 skills.

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 commission-programme

README.md
[![agentmods](https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/commission-programme/github.svg)](https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/commission-programme)
Your own site
<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/commission-programme"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/commission-programme/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 commission-programme

Your own site · 80×15
<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/commission-programme"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/commission-programme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 901 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 $0.00037 $0.00901
Opus 5.5 $0.00015 $0.00360
Sonnet 5.5 $0.00007 $0.00180
Haiku 4.5 $0.00004 $0.00090

Measured 1mo ago against content hash 4a4825291d78, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commission-programme 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 1mo 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.

plugins/sdlc-programme/skills/commission-programme/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commission to Programme

Install the sdlc-programme bundle into a project. Use this when:

  • Team size 11-50 across 2-5 teams
  • Specification maturity is formal or contract-first
  • Blast radius is moderate-to-high
  • Audit-friendly traceability matters but full regulated-industry traceability does not

For other team shapes:

  • 1-2 person projects → use commission-solo (or /sdlc-core:commission --option solo)
  • 3-10 person product teams → use the framework default (no commissioning needed)
  • Regulated industries → use commission-assured (Phase E, future)

Steps

LEVEL="${1:-production}"  # default production for Programme

if [ -n "$1" ] && [ "$1" != "--level" ]; then
    echo "Usage: commission-programme [--level production|enterprise]" >&2
    exit 1
fi
LEVEL="${2:-production}"

case "$LEVEL" in
    production|enterprise) ;;
    *)
        echo "Programme supports levels: production, enterprise" >&2
        exit 1
        ;;
esac

# Delegate to sdlc-core:commission with --option programme --level <LEVEL> --bundle-dir <Programme bundle path>
PROJECT_DIR=$(pwd)
BUNDLE_DIR="$CLAUDE_PLUGIN_ROOT"  # the sdlc-programme plugin's own root inside the container/install

# Sanity check the bundle dir
if [ ! -f "$BUNDLE_DIR/manifest.yaml" ]; then
    echo "Programme bundle manifest not found at $BUNDLE_DIR/manifest.yaml" >&2
    exit 1
fi

python3 << PYEOF
from datetime import datetime, timezone
from pathlib import Path

from sdlc_core_scripts.commission.installer import install_bundle
from sdlc_core_scripts.commission.manifest import parse_manifest
from sdlc_core_scripts.commission.recorder import (
    CommissioningRecord, is_commissioned, write_record,
)

bundle_dir = Path("$BUNDLE_DIR")
project_dir = Path("$PROJECT_DIR")
team_config = project_dir / ".sdlc" / "team-config.json"

manifest = parse_manifest(bundle_dir / "manifest.yaml")

constitution = project_dir / "CONSTITUTION.md"
overwrite = is_commissioned(team_config)
if constitution.exists() and not overwrite:
    print(f"WARNING: {constitution} exists and project is uncommissioned.")
    response = input("Replace existing constitution and commission to Programme? [y/N] ")
    if response.lower() != "y":
        print("Aborted.")
        raise SystemExit(1)
    overwrite = True

result = install_bundle(bundle_dir, project_dir, manifest, overwrite=overwrite)
print(f"Installed {len(result.installed_paths)} files")

record = CommissioningRecord(
    sdlc_option="programme",
    sdlc_level="$LEVEL",
    commissioned_at=datetime.now(timezone.utc).isoformat(),
    commissioned_by="claude-agent",
    option_bundle_version=manifest.version,
)
write_record(team_config, record)
print(f"Commissioned: programme / $LEVEL / {manifest.version}")
PYEOF

Read the full file on GitHub · 110 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. 1mo ago First seen · 110 lines · 37 tokens per session scan A 4a4825291d78

Subscribe to this mod's changes

commission-programme is a skill published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 37 tokens to every session and 901 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 2026-09-03.

Related

Other skills, from other repositories