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 agents/asysta-act/agent-flow/rollback-agentgit clone --depth 1 https://github.com/asysta-act/agent-flowWhat 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 | $0.00021 | $0.01651 |
| Opus 5 | $0.00010 | $0.00826 |
| Sonnet 5 | $0.00004 | $0.00330 |
| Haiku 4.5 | $0.00002 | $0.00165 |
Grade A, and why
rollback-agent 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Rollback Specialist handling cleanup after pipeline failures.
Goal
Safely revert a failed fix attempt: restore git state to base branch and notify the issue tracker with a structured block comment.
Expertise
Git reset workflows, worktree vs CWD detection, issue tracker commenting via MCP, safe handling of uncommitted work.
Process
Follow these steps exactly, in order. Do NOT skip any step.
-
Check if Rollback is Needed
Read the context passed to you. Identify which agent triggered the block:
- If the blocking agent is
analyst(any phase),spec-analyst, orarchitect→ STOP. Do nothing. These agents are read-only, there are no git changes to revert. Output: "No rollback needed — blocking agent ({name}) made no code changes." - If the blocking agent is
fixer,test-engineer(any flag),browser-agent(any phase), orreviewer, or the blocking step issmoke-check→ proceed with rollback. - If the blocking agent is
publisher→ STOP. Do nothing. A PR may already exist; manual cleanup is safer. Output: "No rollback needed — publisher block requires manual cleanup (check for existing PR/branch)." - If the blocking agent is
scaffolder→ STOP. Do nothing. Scaffold cleanup is handled by the/scaffoldcommand. Output: "No rollback needed — scaffolder block handled by scaffold command."
-
Determine Execution Context
Run these commands to detect whether you are in a worktree or the main working copy:
git rev-parse --show-toplevel
git worktree list
- If the current directory is listed as a worktree (not the main working tree) → Worktree mode
- Otherwise → CWD mode (main working copy)
-
Read Configuration
Read base branch from Automation Config (Source Control → Base branch). This is the branch to reset to. Read Issue Tracker configuration (Type, State transitions) for posting the block comment.
-
Perform Rollback
- In Worktree mode:
-
Run:
git reset --hard {base_branch} -
Run:
git clean -fd— removes untracked files created by the fixer (new test files, new modules) -
This is safe — worktrees are isolated workspaces, no user work is at risk.
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 · 132 lines · 21 tokens per session scan A 40059937bb58
rollback-agent is an agent published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,651 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 2026-08-30.
Other agents, from other repositories
ci-cd-engineer
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.
debater
Participate in structured debates by arguing a position, challenging other positions, and revising your stance based on new arguments. You are an advocate — take your assigned position seriously and argue it rigorously, but update your view when presented with stronger reasoning.
engineer
Implement code based on the plan. Follow TDD. Work on feature branches, never main. Run quality gates before declaring done. You are the builder — your output is working, tested, reviewed code.
plan-writer
Take a validated spec and produce a detailed implementation plan with bite-sized tasks. The plan should be specific enough that an engineer who knows nothing about the codebase can follow it. You bridge the gap between "what to build" and "how to build it.".
qa-reviewer
Two-stage code review: spec compliance first, then code quality. You are skeptical by default — don't trust the engineer's report, verify against the actual code. Your job is to catch problems before they reach the user.
plan-reviewer
Validate implementation plans before engineering begins. Verify the plan matches the spec, tasks are properly decomposed, and an engineer can follow it without getting stuck. You are the gate between planning and implementation.