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 verify-agent-readinessgit 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/verify-agent-readiness)<a href="https://agentmods.dev/skills/bikeread/promethos/verify-agent-readiness"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/verify-agent-readiness/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/verify-agent-readiness"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/verify-agent-readiness.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 | $0.00026 | $0.00612 |
| Opus 5 | $0.00013 | $0.00306 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
verify-agent-readiness 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Prevent false completion by tying every positive claim to fresh verification evidence.
Inputs
- Claimed change or fix
- Relevant requirements or acceptance criteria
- Available verification commands, tests, or manual checks
Non-Goals
- Assuming the implementation is correct because the code looks clean
- Treating partial checks as proof of total correctness
- Replacing a broader workflow library's generic merge-readiness or completion-verification path when coexistence rules already assign it there
Workflow
Trigger signals (for proactive recognition)
- You are about to say "done" or "complete"
- The user says "差不多了吧" or "is it ready"
- A fix was applied but not re-tested
- Acceptance criteria exist but have not been checked with fresh evidence
- Someone is about to claim completion based on inspection alone
- The user explicitly asks PromethOS to verify an agent-domain deliverable, eval pack, autonomy policy, or agent-system change before calling it ready
1. Translate each claim into a check
List the specific requirement, fix, or success statement you are about to make and map it to a test, command, transcript check, or manual verification step. Success criteria: Every major claim has a named verification path.
2. Run fresh verification
Execute the relevant checks now, not from memory, old logs, or assumed behavior. Success criteria: The evidence is fresh and tied directly to the current state of the work.
3. Check for scope gaps and regressions
Verify not only the changed behavior but also the nearby assumptions most likely to have been broken or left unverified. Success criteria: Verification covers both the target claim and the most probable adjacent breakage.
4. Report the real status, not the hopeful one
State what is verified, what remains unverified, and what the evidence actually supports. If a stronger session-level workflow system already owns generic merge-readiness in coexistence mode, say so explicitly instead of pretending PromethOS should override it by default. Success criteria: The final report is aligned with evidence rather than optimism.
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.
- 9d ago First seen · 77 lines · 26 tokens per session scan A 5a101166550d
verify-agent-readiness is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 612 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.