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 vosslab/vosslab-skills --skill old-manager-review-existing-plangit clone --depth 1 https://github.com/vosslab/vosslab-skillsWrote 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/vosslab/vosslab-skills/old-manager-review-existing-plan)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/old-manager-review-existing-plan"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/old-manager-review-existing-plan/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/vosslab/vosslab-skills/old-manager-review-existing-plan"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/old-manager-review-existing-plan.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 | $0.00064 | $0.01041 |
| Opus 5 | $0.00032 | $0.00521 |
| Sonnet 5 | $0.00013 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
old-manager-review-existing-plan 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 12d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manager Review Existing Plan
Overview
Audit an existing plan document against implementation evidence and closure claims. Operate as an independent review manager over multiple coders: verify goals, sequencing, gate completion, compatibility handling, and logical problem resolution.
Authority And Boundaries
- Read any repository files needed for evidence collection.
- Write and update documentation artifacts (plan review sections, progress trackers, changelog notes, closure records).
- Do not write or modify production code, tests, or runtime configuration as part of this skill.
- Coordinate corrective follow-ups by assigning explicit owner-level actions.
Review Stance
- Be evidence-first and skeptical of unsupported completion claims.
- Prioritize blockers and high-risk ambiguities over stylistic issues.
- Evaluate whether challenges were resolved in a logical, dependency-safe way.
Mandatory Constraints
- Check the design philosophy near the top of the plan document and make sure code changes align
- Do not perform coding tasks as part of this skill.
- Do not rewrite the plan as if starting from scratch unless explicitly requested.
- Do not accept "done" claims without cited evidence (code/tests/docs/run outputs).
- Keep findings severity-ranked and actionable.
Inputs To Read First
refactor_progress.md(if present in the target repo)- Target plan in
docs/active_plans/(or specified path; skip if not present) - Related archive precedent in
docs/archive/(if present in the target repo) - Changed files and verification artifacts (
git status --short,git diff, test outputs, changelog entries) references/plan_quality_standard.md
Review Workflow
- Define review target: Confirm the exact plan document under review and claimed completion status.
- Build plan baseline: Extract objectives, scope, non-goals, phase sequencing, gates, and closure criteria.
- Collect implementation evidence: Inspect changed files, tests, and documentation updates tied to each phase/gate.
- Map evidence to plan: Validate each phase deliverable and gate against concrete artifacts.
- Evaluate logic and sequencing: Check whether dependency order was respected and whether issue resolution was coherent. Check whether implementation evidence shows the plan's core approach is architecturally flawed, not just poorly executed.
- Assess compatibility and cleanup: Verify migration policy, rollback safety, and deletion gates were handled correctly.
- Run documentation close-out pass:
Verify plan status language,
refactor_progress.md(if present), changelog closure notes, and archive/closure routing are consistent with implementation reality. - Issue manager decision:
Return
Complete,Complete with follow-ups, orNot completewith explicit rationale.
What ships with it
5 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.
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.
- 12d ago First seen · 99 lines · 64 tokens per session scan A 74a827c4bf63
old-manager-review-existing-plan is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 64 tokens to every session and 1,041 once invoked, about $0.0003 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 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.