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 Chisiki1/objective-integrity-framework --skill objective-supervisor-controlgit clone --depth 1 https://github.com/Chisiki1/objective-integrity-frameworkWrote 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/chisiki1/objective-integrity-framework/objective-supervisor-control)<a href="https://agentmods.dev/skills/chisiki1/objective-integrity-framework/objective-supervisor-control"><img src="https://agentmods.dev/badge/skills/chisiki1/objective-integrity-framework/objective-supervisor-control/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/chisiki1/objective-integrity-framework/objective-supervisor-control"><img src="https://agentmods.dev/badge/skills/chisiki1/objective-integrity-framework/objective-supervisor-control.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 | $0.00058 | $0.00558 |
| Opus 5.5 | $0.00023 | $0.00223 |
| Sonnet 5.5 | $0.00012 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
objective-supervisor-control 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 1mo 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.
What it actually says
Objective supervisor control
Use when the primary owner consumes a job event, decides a source-bound correction or evaluates a wait. The historical name does not require separate Supervisor/Worker chats. Independent refutation remains separate from this self-control pass. It is not a tool interceptor and does not authorize edits or external actions.
Provide the frozen objective, event identity, objective evidence delta, omission consequence, shorter alternative, induced rework, exact return step, and later-effect plan. Run python -B scripts/supervisor_control.py --input <event.json>.
The requested decision may be WATCH, CONSUME, REFUTE, CORRECT, USER_DECISION, WAIT_AT_DECISION_WINDOW, or v2 ACT. The script returns ADMIT or HOLD and the requested decision; neither is outcome proof. A status-only event or fixed polling returns a dependent hold. Slow work with stated evidence progress may wait at a bounded decision window.
For source-wide implementation, use objective-supervisor-control-v2: v1 event fields plus source_sha256, owner_chat_id, and work_phase. Read the sibling lifecycle Skill's references/source-wide-execution.md; bind the same exact owner scope/state used by work_io and transition admission. ACT selects the bound action. CORRECT must bind REPAIR_FINDINGS, not a first finding while the whole sweep is still collecting. Inspect the returned work_phase.next_actions and act on the eligible implementation, remaining check or grouped repair; do not merely save the result. V1 remains readable for legacy/ordinary non-product events, with explicit absence of source-wide evaluation. Raw and unknown action effects remain in the authoritative ledger even when new work is held.
At an integration gap, repeated causal family or support-heavy result, also apply the installed lifecycle Skill's references/convergence.md. Use existing fields to identify the next required consumer connection, valid unchanged evidence, changed action or handoff, and return step. Consume eligible components into the actual deliverable before accumulating disconnected work when that has higher value. Preserve useful independent work and component proof ceilings; never require full runtime completion for every finite unit. A control record alone is not a correction: carry the chosen source-authorized change to its next real use and assess its effect. This is event-driven and adds no packet, fixed time limit, automatic restart or new authority.
What ships with it
2 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.
- 1mo ago Changed · -4 lines da1224a94cae
- 1mo ago Changed · +4 lines 6433dba81e51
- 1mo ago First seen · 17 lines · 58 tokens per session scan A 8d2bb5914bd8
objective-supervisor-control is a skill published in the GitHub repository Chisiki1/objective-integrity-framework (23 stars, last pushed 8d ago), licensed Apache-2.0. It adds 58 tokens to every session and 558 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 2026-09-08.
Other skills, from other repositories
marx
A coding-agent skill that uses Marxist ideas to examine research, engineering, project, debugging, retrospective, and organizational problems. It turns concepts such as root cause and the main contradiction into a practical analysis.
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.
ads-youtube
Audit YouTube Ads campaign setup, video inventory, Shorts, in-stream, CTV, creative, audiences, brand safety, bidding, and measurement. Use for YouTube Ads, video ads, pre-roll, bumper ads, skippable in-stream, Shorts ads, VAC migration, or CTV. Read-only; use ads-google for Google-managed campaign types and…
ads-launch
Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.