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 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/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/mperkhou/career-agent-workbench/agentic-workflow-controller"><img src="https://agentmods.dev/badge/skills/mperkhou/career-agent-workbench/agentic-workflow-controller.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 | $0.00062 | $0.00543 |
| Opus 5.5 | $0.00025 | $0.00217 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 62 tokens to every session and 543 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 2026-08-31.
Other skills, from other repositories
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…
cloudflare-deploy
Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.
job-description-skill
A job-description analysis skill that turns a vacancy listing and a candidate’s background into an HTML report about fit, gaps, interview topics, and application strategy.
offer-compare-skill
A decision assistant for comparing two or more job offers across pay, growth, company strength, team risk, promotion, AI exposure, and lifestyle. Total compensation means the combined value of salary, bonuses, shares, and sign-on payments.
multi-program-manager
Manage and compare multiple affiliate programs as a portfolio. Triggers on: "manage my affiliate programs", "compare my programs", "portfolio overview", "which program should I focus on", "diversify my affiliate income", "program switching", "affiliate portfolio", "program comparison", "revenue allocation", "which…