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 wahidyankf/ose-public --skill plan-verifying-executiongit clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/plan-verifying-execution)<a href="https://agentmods.dev/skills/wahidyankf/ose-public/plan-verifying-execution"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/plan-verifying-execution/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/wahidyankf/ose-public/plan-verifying-execution"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/plan-verifying-execution.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 | $0.00045 | $0.00948 |
| Opus 5.5 | $0.00018 | $0.00379 |
| Sonnet 5.5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
plan-verifying-execution 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying Plan Execution
Full post-execution validation methodology for plan-execution-checker: confirms a completed plan's
implementation matches what was promised, and that every execution-time gate actually held.
Reference Modules
reference/01-validation-scope.md— Validation Scope (Requirements Coverage, Technical Documentation Alignment, Delivery Checklist Completion, Code Quality, Integration Validation).reference/02-workflow-overview.md— Workflow Overview (Steps 0-7).reference/03-operational-readiness-execution.md— Step 5b (Operational Readiness Execution) verification.reference/04-manual-assertions-ui-api-e2e-locale.mdandreference/05-manual-assertions-evidence-and-retests.md— Step 5c (Manual Behavioural Assertions) verification: UI/API/end-to-end/locale checks, evidence capture, and Rule-15/Rule-16 retests.reference/06-plan-archival.md— Step 5d (Plan Archival and README Updates) verification.reference/07-worktree-verification-declaration-and-history.mdandreference/08-worktree-verification-freshness-cleanup-and-cap.md— Step 5e (Worktree Usage) verification.reference/09-phase-gate-and-execution-marker.md— Step 5f-gates (Phase Gate and Execution Marker) post-execution verification.reference/10-anti-hallucination-verification.md— Step 5f (Anti-Hallucination) post-execution verification.reference/11-knowledge-capture-terminal-states.mdandreference/12-knowledge-capture-audit-and-severity.md— Step 5h (Knowledge Capture Routing, blocking gate) verification.reference/delivery-mode-pr-ci.mdandreference/delivery-mode-phase0-and-boundaries.md— Step 5i delivery-mode, exact-head PR-CI, optional-review, Phase 0, and boundary verification.
Core Principles
This is the final quality gate — be thorough, independent, and uncompromising. Every rule
states its own criticality per finding, not a blanket file-level severity. Post-execution
re-checks, not re-derives: plan-checker validates the plan is well-formed at authoring time;
this skill validates execution actually did what the well-formed plan said, against the
post-execution repo state (git log, CI status, delivered files) — the finding types overlap in name
but the evidence source never does. Blocking gates block archival unconditionally — Knowledge
Capture (Step 5h) and any CRITICAL finding halt archival regardless of how many other checks passed.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 434 B
- reference/anti-hallucination-verification.md 3.9 KB
- reference/delivery-mode-phase0-and-boundaries.md 3.3 KB
- reference/delivery-mode-pr-ci.md 2.7 KB
- reference/knowledge-capture-audit-and-severity.md 3.2 KB
- reference/knowledge-capture-terminal-states.md 2.9 KB
- reference/manual-assertions-evidence-and-retests.md 3.7 KB
- reference/manual-assertions-ui-api-e2e-locale.md 3.0 KB
- reference/operational-readiness-execution.md 4.2 KB
- reference/phase-gate-and-execution-marker.md 2.5 KB
- reference/plan-archival.md 1.4 KB
- reference/README.md 2.3 KB
- reference/validation-scope.md 3.9 KB
- reference/workflow-overview.md 1.5 KB
- reference/worktree-verification-declaration-and-history.md 1.9 KB
- reference/worktree-verification-freshness-cleanup-and-cap.md 5.6 KB
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 · 69 lines · 45 tokens per session scan A 415918f11557
plan-verifying-execution is a skill published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 948 once invoked, about $0.0002 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 2026-10-14.
Other skills, from other repositories
modern-tooling
Opinionated tooling and conventions for modern JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier, monorepos, library publishing, or establishing coding standards.
V3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
insta-snapshots
Review and update Oxc Insta snapshots non-interactively after expected output changes or snapshot test failures.
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.
walkeros-testing-strategy
Use when writing tests, reviewing test code, or discussing testing approach for walkerOS packages. Covers env pattern, dev examples, and package-specific strategies.