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 skills/ocentra/ocentra-enforcer/plannpx skills add ocentra/ocentra-enforcer --skill plangit clone --depth 1 https://github.com/ocentra/ocentra-enforcerWrote 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/ocentra/ocentra-enforcer/plan)<a href="https://agentmods.dev/skills/ocentra/ocentra-enforcer/plan"><img src="https://agentmods.dev/badge/skills/ocentra/ocentra-enforcer/plan.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.02178 |
| Opus 5 | $0.00029 | $0.01089 |
| Sonnet 5 | $0.00012 | $0.00436 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade A, and why
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 4d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
workflow: "enforcer plan new <name> (b01 scaffold) -> author workpacks -> enforcer plan check (b02 validate) -> orchestrate (b04)"
doctrine: "rules are conditions, enforcement is mechanical (T1 hard-block / T2 warn-surface / T3 review-assist), no prose-without-check"
scaffolder: "crates/enforcer-plan/src/scaffolder.rs::scaffold_plan -- deterministic, refuses overwrite without force, checklist DERIVED from caller ScopeFacts (L24: never sibling copy-paste)"
validators:
PLAN-CAPSULE.1: "crates/enforcer-plan/src/validator.rs::PlanCapsuleValidator -- exact agent-capsule marker block, only Doc: line varies"
PLAN-SKELETON.1: "crates/enforcer-plan/src/validator.rs::PlanSkeletonValidator -- required section headings present, in order"
PLAN-FRONTMATTER.1: "crates/enforcer-plan/src/validator.rs::PlanFrontmatterValidator -- owns/deps/tier lines well-formed, tier in P0..P5 [+ T1..T3]"
PLAN-PARALLEL.1: "crates/enforcer-plan/src/validator.rs::check_parallel_safety -- no-dep-edge workpacks must have disjoint owns globs"
PLAN-RESUME.1: "crates/enforcer-plan/src/validator.rs::PlanResumeStateValidator -- Where We Are + CHECKLIST/TASKLIST/PROGRESS + PREV/NEXT present"
PLAN-DRIFT.1: "crates/enforcer-plan/src/validator.rs::check_checklist_drift -- checklist must not contradict this doc's own Where We Are (L24)"
templates: "crates/enforcer-plan/templates/*.tpl via crates/enforcer-plan/src/templates.rs -- frozen, include_str!, {{placeholder}} substitution, no inline capsule literal outside this dir"
self_validate: "crates/enforcer-plan/tests/self_validate.rs -- runs the live PLAN-* Validator set against docs/plans/enforcer-selfhost-plan/ (this plan's OWN capsule/skeleton/frontmatter files); zero Finding assertion scoped to the files this pack owns, non-gating report over sibling docs it does not own"
dispatch: "/plan command (crates/enforcer-install/src/commands/plan.rs) emits a harness command whose body invokes `enforcer plan new`/`enforcer plan check` via the real enforcer binary -- never a hand-written per-harness hook, never a stub that fakes success"
cli_status: "enforcer plan is a RESERVED clap subcommand (crates/enforcer-cli/src/main.rs Command::Plan) not yet wired to enforcer-plan's scaffolder/validator -- a known, separate gap outside this skill's owns-set; the emitted command still targets the real binary invocation, not a workaround"
banned: "hardcoded checklist boilerplate copy-pasted from a sibling workpack (L24); inline capsule literal outside templates/; a /plan dispatch that short-circuits to a fixed/fake result"
Use this skill to create a new plan directory, author or audit workpacks against this repository's Ocentra-methodology contract, and self-validate a plan mechanically instead of trusting prose review.
The methodology used to live as tribal knowledge and scattered prose: the
capsule contract, the scaffold/validate loop, and the disjoint-ownership rule
for parallel work were things people remembered rather than things a machine
checked. This skill closes that gap by wiring the mechanical backing
(enforcer-plan's scaffolder and PLAN-* validators) into one documented
workflow and a self-validating cargo test.
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.
- 4d ago First seen · 135 lines · 58 tokens per session scan A 467937b5e9e5
plan is a skill published in the GitHub repository ocentra/ocentra-enforcer (0 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 2,178 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…