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.
git clone --depth 1 https://github.com/transparent-pegasus/herdrpowersWrote 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.
[](https://agentmods.dev/commands/transparent-pegasus/herdrpowers/strict_full_cycle)<a href="https://agentmods.dev/commands/transparent-pegasus/herdrpowers/strict_full_cycle"><img src="https://agentmods.dev/badge/commands/transparent-pegasus/herdrpowers/strict_full_cycle.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00606 |
| Opus 5 | $0.00012 | $0.00303 |
| Sonnet 5 | $0.00005 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
strict_full_cycle 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 8d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/strict_full_cycle Workflow
Run the /full_cycle workflow exactly as written: read full_cycle.md — the workflow file next to this one in the pack's commands/ directory — and follow every step, rule, and execution requirement in it. This file adds one override and nothing else.
The Override
Every review gate runs, whatever .herdrpowers/config.yaml says.
Resolve the configuration the way orchestration describes — the repository's .herdrpowers/config.yaml first, orchestration/roles.yaml for anything it omits — and then ignore enabled on every review task in the resolved result. Each counts as enabled: true for this run, including any review task a later pack release adds. /full_cycle's "when it is disabled, skip" clauses therefore never fire here.
Nothing else changes. role and mode still bind for every task, as do roles:, fallbacks:, and delegation: — strict mode does not widen delegation.pane_scope to find a pane for a forced-on gate, and does not change delegation.execution. Strict mode overrides one key: it never reassigns a role, changes a mode, or relaxes an invariant — review independence remains the reset session (not pane identity), and a review whose role binds to a list of agent types still runs once per entry.
Never write the configuration file. enabled: false stays where the user put it; this run declines to honor it and says so in the report.
What Forcing a Gate On Cannot Do
A gate still needs a pane. If the role a review resolves to has no available agent type — an empty agents: list, or no idle pane of any listed type — the gate degrades exactly as orchestration's "Roles that bind to a list" and "Exhaustion and fallback" sections describe. Forced on is a decision, not a guarantee that the review happened; the report names what actually ran.
Reporting
/full_cycle's final report already names every non-default assignment and every disabled review. Add one section to it: Review gates forced on by strict mode — each review task whose resolved enabled was false, run anyway, with what the repository's configuration said. If no gate was disabled, say so plainly: strict mode changed nothing, and this run is identical to /full_cycle.
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.
- 8d ago First seen · 30 lines · 23 tokens per session scan A 090afff6bff4
strict_full_cycle is a command published in the GitHub repository transparent-pegasus/herdrpowers (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 23 tokens to every session and 606 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 commands, from other repositories
amend-plan
Plan Amend - Discuss and apply amendments to a plan.json implementation plan.
report-issue
Open a atomic GitHub issue via gh. Bug report or feature request — auto-detect from user's description.
ab
Show Kanban board or list view (shortcut for board).
archive-tasks.en
Archive completed tasks into a date-organized workspace directory.
block-task.en
Mark a task as blocked and record the reason.
init-milestones.en
Initialize the repository's standard milestones taxonomy.