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/mperkhou/career-agent-workbench/agentic-workflow-controllernpx skills add mperkhou/career-agent-workbench --skill agentic-workflow-controllergit clone --depth 1 https://github.com/mperkhou/career-agent-workbenchWrote 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/mperkhou/career-agent-workbench/agentic-workflow-controller)<a href="https://agentmods.dev/skills/mperkhou/career-agent-workbench/agentic-workflow-controller"><img src="https://agentmods.dev/badge/skills/mperkhou/career-agent-workbench/agentic-workflow-controller.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 | $0.00062 | $0.00543 |
| Opus 5 | $0.00031 | $0.00271 |
| Sonnet 5 | $0.00012 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
agentic-workflow-controller 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 3d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Workflow Controller
Follow root AGENTS.md. The committed plan is authoritative; the ignored
tracker is only a bound cursor and evidence log. This controller never turns a
tracker flag into permission to publish, mutate private application state, or
perform release closeout.
Resume an initialized workflow
-
Read root guidance, the complete committed plan, and the complete tracker.
-
Validate the tracker and plan digest before relying on its cursor:
.venv/bin/python skills/agentic-workflow-controller/scripts/workflow_state.py \ validate tmp/agentic-workflows/<workflow-id>/tracker.json -
Identify the current P step or G gate and record
beginbefore mutation. -
Execute only the authorized step and path/state boundary.
-
Collect sanitized evidence before
completeorgate. -
Pause on plan-digest drift, scope change, failed invariant, missing authority, private-state risk, or release action requiring approval.
The helper supports status, inspect, validate, begin, complete,
gate, pause, resume, rebind-plan, artifact manifests, and evidence-route
lifecycle commands. It does not push, merge, tag, call providers, mutate live
tracker rows, or operate as a daemon.
Evidence routes and artifacts
Use read-only evidence routes for bounded independent checks such as code-path audits, schema comparisons, package metadata, or rendered-layout inspection. The main implementor owns edits, live/private mutation, commits, PR changes, and gate decisions.
Store only small sanitized control evidence beneath ignored
tmp/agentic-workflows/<workflow-id>/. Put databases, PDFs, screenshots, raw
logs, token stores, credentials, runtime homes, and other heavy/private
artifacts beneath a disposable system temporary directory such as
$TMPDIR/career-agent-workbench-agentic/<workflow-id>/.
Plan amendments and closeout
Gate amendments affect incomplete work only. Update the committed plan and
matching changelog entry together, commit them normally, then use
rebind-plan. Preserve completed history. Never amend, rebase, squash, merge,
tag, publish, deploy, or contact an external party without the plan's explicit
boundary and current user authority.
What ships with it
7 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.
- 3d ago First seen · 54 lines · 62 tokens per session scan A 1192e9b50cac
agentic-workflow-controller is a skill published in the GitHub repository mperkhou/career-agent-workbench (0 stars, last pushed 29d ago), licensed MIT. It adds 62 tokens to every session and 543 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
html-ppt-zhangzara-capsule
A year-end self-review for a product manager — the role, the outcomes, the learning, and the ask, all evidence-backed. Built as a decision-grade career deck for manager, review committee.
enferno-dev
Development skill for Enferno Flask framework. Use when implementing features, fixing bugs, or writing code for Enferno-based applications. This includes creating models, API endpoints, Vue.js frontend components, database operations, or any development task within the Enferno ecosystem. Triggers: creating blueprints…
figma-use
MANDATORY prerequisite — you MUST invoke this skill BEFORE every usefigma tool call. NEVER call usefigma directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in…
cli-creator
Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a…
evaluate
Evaluate how well a job posting matches your background. Paste a JD or URL and get an honest A-F scored assessment with match analysis, compensation research, positioning strategy, and interview prep. Use when someone says 'evaluate this job', 'should I apply', 'how well do I match', 'rate this job', or pastes what…
apply
Help fill out a job application form. Generates personalized answers for every field using your profile and evaluation. Never auto-submits. Use when someone says 'help me apply', 'fill out this application', or 'application for'.