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 skills add bikeread/promethos --skill trim-agent-scopegit clone --depth 1 https://github.com/bikeread/promethosWrote 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/skills/bikeread/promethos/trim-agent-scope)<a href="https://agentmods.dev/skills/bikeread/promethos/trim-agent-scope"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/trim-agent-scope/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bikeread/promethos/trim-agent-scope"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/trim-agent-scope.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00027 | $0.00664 |
| Opus 5.5 | $0.00011 | $0.00266 |
| Sonnet 5.5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
trim-agent-scope 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Protect the smallest useful scope so the system remains buildable, testable, and understandable.
Inputs
- Current goal or plan
- New ideas, additions, or exceptions
- Existing design boundaries
Non-Goals
- Rejecting every improvement automatically
- Treating simplicity as the same thing as incompleteness
Workflow
Trigger signals (for proactive recognition)
- A plan or skill keeps gaining sections without removing old ones
- The user says "越搞越复杂" or "this keeps getting bigger"
- A CLAUDE.md or system prompt exceeds the length that made it effective
- You catch yourself adding a "nice to have" not in the original goal
1. Restate the smallest useful job
Write the one thing this plan, skill, or agent must accomplish right now, and state the minimum acceptable result that still makes the work worthwhile. Success criteria: The core job can be summarized in one sentence and the minimum useful outcome is explicit.
2. Test each addition against the current job
For every new idea, ask whether it is required to make the core job work, a dependent enabler, a future enhancement, or a separate problem entirely. Treat "nice to have" as a reason to defer unless it unblocks the present goal. Success criteria: Every addition is labeled as now, later, or never, with a reason that points back to the core job.
3. Remove or isolate non-essential scope
Cut side quests, split out unrelated work, and capture deferred items in a short list so they do not leak back into the current slice. Protect dependencies that are necessary for the core job, but do not let them become justification for a larger project. Success criteria: The remaining scope is smaller without losing the ability to solve the actual problem.
4. Set stop rules for growth
Define the point where added detail, extra features, or edge-case handling should stop for this version. If the project starts needing a second system, a second skill, or a second milestone to stay coherent, stop and re-scope. Success criteria: The plan has an explicit boundary that prevents quiet scope creep from becoming the new normal.
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.
- 2mo ago First seen · 76 lines · 27 tokens per session scan A 16f0ef320a4f
trim-agent-scope is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 664 once invoked, about $0.0001 per session on Opus 5.5. 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.
trim-agent-scope compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trim-agent-scopebikeread/promethos | Skill | 33 | 7mo ago | MIT | A | 27 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |