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/baodq97/open-plugin/revisitgit clone --depth 1 https://github.com/baodq97/open-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 | $0.00010 | $0.00339 |
| Opus 5 | $0.00005 | $0.00169 |
| Sonnet 5 | $0.00002 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
revisit 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
Revisit an earlier Design Thinking phase.
Instructions
- Read
.design-thinking/state.yamlto get the active workspace - Read
{workspace}/state.yamlto get the current phase - Parse the target phase from the command argument (e.g.,
/design-thinking:revisit empathize) - Validate:
- Target phase must be before or equal to current phase
- Valid phases: empathize, define, ideate, prototype, prd
- Reset target phase:
- For empathize/define/ideate: set status to
engaging, phase_step toengage - For prototype: set status to
engaging, phase_step toengage - For prd: set status to
synthesizing, phase_step tosynthesize - Reset
rework_count: 0,qg_verdict: null,qg_history: [] - Preserve
conversation_turns(don't reset — accumulated total)
- For empathize/define/ideate: set status to
- Reset all phases AFTER the target phase to
not_started:- Reset status, conversation_turns, rework_count, qg_verdict, qg_history
- Update
current_phaseandphase_step - Do NOT delete existing artifact files — they remain for reference
- Add history entry: "Revisited {target_phase} phase"
- Report: "Returned to {target_phase} phase. Later phases reset to not_started. Previous artifacts preserved for reference."
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 · 28 lines · 10 tokens per session scan A 4f22ab8994ad
revisit is a command published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 339 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
derive-tests
Turn documented intent into a test-coverage map — inventory the tests that exist today, derive use-case cases from the system docs, separate existing coverage from proposed tests and unverified gaps, mark each unit / guarded-live / manual, and recommend a green-before-merge CI gate.
ship-check
Turn a vibe-coded repo into a reviewer-ready shipping packet — document the app, wire agent context, run security and performance audits, map test coverage, and compile the results.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-prd
Create a comprehensive Product Requirements Document from a feature idea or problem statement.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.