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.
npx agentmods add commands/ai-sdlc-framework/ai-sdlc/rebasegit clone --depth 1 https://github.com/ai-sdlc-framework/ai-sdlcWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.03983 |
| Opus 5 | $0.00023 | $0.01992 |
| Sonnet 5 | $0.00009 | $0.00797 |
| Haiku 4.5 | $0.00005 | $0.00398 |
Grade A, and why
rebase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rebase PR #$ARGUMENTS onto latest origin/main by spawning the
rebase-resolver subagent. This command exists because manual rebase
loops were eating significant orchestrator time across PRs #113, #114,
and #115 (AISDLC-105). The mechanical 80% (CHANGELOG overlaps, test
additions, prettier drift) is delegated to the subagent; the
architectural 20% (modify-vs-delete, semantic conflicts, verification
failures) escalates back here for human attention.
Why this command lives in the slash command body (not a subagent middleman)
Same reason as /ai-sdlc execute: plugin subagents cannot use the
Agent tool (the harness filters it out one level deep regardless of
frontmatter — empirical proof in AISDLC-69.2 / AISDLC-98). The slash
command body runs in the main Claude Code session which DOES have
Agent, so it can spawn rebase-resolver directly.
Hard rules (NEVER violate)
- Never merge a PR. Do not run
gh pr merge. - Never force-push with plain
--force/-f. Always use--force-with-lease(mirrors agent-role.yaml block list). - Never push to
mainormaster. Refuse early. - Never close PRs or issues. No
gh pr close,gh issue close. - Never delete branches. No
git branch -D/-d. - Never edit
.ai-sdlc/**or.github/workflows/**. - Never write GitHub Actions CI-skip magic tokens (AISDLC-88) — the
five literal substrings (
[skip ci],[ci skip],[no ci],[skip actions],[actions skip]) silently disable workflows. The re-attestation chore commit body composed by Step 5 below is sanitised the same way/ai-sdlc executeStep 10 sanitises it.
Step 0 — Validate input
PR=$ARGUMENTS
if [ -z "$PR" ] || ! echo "$PR" | grep -qE '^[0-9]+$'; then
echo "ERROR: pass a PR number, e.g. /ai-sdlc rebase 115"
exit 1
fi
Step 1 — Locate PR + worktree
gh pr view "$PR" --json number,title,headRefName,headRefOid,body,state \
> /tmp/rebase-pr-${PR}.json
BRANCH=$(jq -r '.headRefName' /tmp/rebase-pr-${PR}.json)
HEAD_SHA=$(jq -r '.headRefOid' /tmp/rebase-pr-${PR}.json)
TITLE=$(jq -r '.title' /tmp/rebase-pr-${PR}.json)
# Refuse on main/master (Hard Rule 3).
if [ "$BRANCH" = "main" ] || [ "$BRANCH" = "master" ]; then
echo "ERROR: refusing to rebase $BRANCH — protected branch"
exit 1
fi
# Derive task ID from branch (pattern: ai-sdlc/<prefix>-<numeric>[.<sub>]-<slug>).
# IMPORTANT: this regex MUST be portable across BSD sed (macOS) and GNU sed
# (linux). BSD sed has no `+?` non-greedy quantifier, and even on GNU sed
# `+?` would stop at the first dash, mangling task IDs like `aisdlc-105`
# down to `aisdlc`. Use an explicit `<letters>-<digits-and-dots>` shape
# instead — captures `aisdlc-105`, `aisdlc-100.2`, etc.
TASK_ID_LOWER=$(echo "$BRANCH" | sed -E 's|^ai-sdlc/([a-z]+-[0-9.]+).*|\1|')
WORKTREE_PATH=".worktrees/$TASK_ID_LOWER"
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.
- 3d ago First seen · 346 lines · 47 tokens per session scan A 0fdb151de827
rebase is a command published in the GitHub repository ai-sdlc-framework/ai-sdlc (92 stars, last pushed 9d ago), licensed Apache-2.0. It adds 47 tokens to every session and 3,983 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.
Other commands, from other repositories
spec-intake
Execute the canonical workflow: .agent/workflows/spec-intake.md.
research
Research a technical or product question.
at-dsgvo
You are helping an enterprise architect generate an Austrian Data Protection Assessment — the Austrian-specific GDPR layer applied by the Datenschutzbehörde (DSB) under the Datenschutzgesetz (DSG 2018, BGBl. I Nr. 165/1999 as amended). Run this after /arckit:eu-rgpd to add Austrian obligations that go beyond the EU…
au-soci-cirmp
You are an enterprise architect generating a Security of Critical Infrastructure Act 2018 (SOCI Act) / Critical Infrastructure Risk Management Program (CIRMP) governance and evidence pack for an Australian critical infrastructure asset or potentially regulated entity.
au-aescsf
You are an enterprise architect generating an Australian Energy Sector Cyber Security Framework (AESCSF) maturity assessment for an Australian energy-sector project, asset, market interface, OT environment, DER platform, or regulated energy business capability.
au-disp-attestation
You are an enterprise architect generating a DISP (Defence Industry Security Program) Member self-attestation pack for an Australian organisation supplying products or services to Defence.