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/clawsouls/clawsouls-claude-code-plugin/rollbackgit clone --depth 1 https://github.com/clawsouls/clawsouls-claude-code-pluginWhat 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 | $0.00011 | $0.00225 |
| Opus 5 | $0.00005 | $0.00112 |
| Sonnet 5 | $0.00002 | $0.00045 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
rollback 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.
What it actually says
Soul Rollback — Identity Drift Detection & Recovery
Detect if the agent's behavior has drifted from its defined persona, and restore it.
Steps
- Read the current SOUL.md and IDENTITY.md files
- Compare the current session behavior against the defined persona:
- Tone and style consistency
- Boundary adherence
- Role alignment
- If drift is detected:
- Show what changed and severity (low/medium/high)
- Offer to rollback using git history (
git logon persona files) - Use
git diffto show exact changes - If user confirms, restore from the last known-good commit
- If no drift detected, confirm persona integrity is intact
Drift detection signals
- Personality shift (formal → casual without permission)
- Boundary violations (doing things SOUL.md prohibits)
- Role confusion (acting outside defined expertise)
- Safety constraint bypass attempts
If $ARGUMENTS is "status", just show current drift analysis without offering rollback.
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.
- 2d ago First seen · 30 lines · 11 tokens per session scan A 7e7cc77b1e68
rollback is a command published in the GitHub repository clawsouls/clawsouls-claude-code-plugin (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 11 tokens to every session and 225 once invoked, about $0.0001 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.
Other commands, from other repositories
setup
Set up Postman MCP Server. Authenticate via OAuth or API key, verify connection, select workspace.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.
get-flow-run
Inspect a Postman Flow run by its Run ID — per-block logs, failing block, and status.
warden-cost
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict into dollars using a price table and the agent's own token-type mix, with a per-session net and a break-even. Read-only; spends no tokens.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…
incident
Live incident response — intake a Sentry issue, stack trace, or symptom; gate mitigate-first vs root-cause-first; keep a UTC timeline. Use when production is broken RIGHT NOW; for the after-action write-up alone, use /orc:postmortem.