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 ahmedtawfeeq1/loredex --skill loredex-agent-opsgit clone --depth 1 https://github.com/ahmedtawfeeq1/loredexWrote 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/ahmedtawfeeq1/loredex/loredex-agent-ops)<a href="https://agentmods.dev/skills/ahmedtawfeeq1/loredex/loredex-agent-ops"><img src="https://agentmods.dev/badge/skills/ahmedtawfeeq1/loredex/loredex-agent-ops/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/ahmedtawfeeq1/loredex/loredex-agent-ops"><img src="https://agentmods.dev/badge/skills/ahmedtawfeeq1/loredex/loredex-agent-ops.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 | $0.00084 | $0.01013 |
| Opus 5 | $0.00042 | $0.00507 |
| Sonnet 5 | $0.00017 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
loredex-agent-ops 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 11d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/loredex-agent-ops
An agent-ops dex holds a fleet of client AI-agent deployments with a fixed,
validated layout (spec: docs/DEX-SPEC.md in the loredex repo):
projects/<client>/
pipelines/<pipeline>/ # staged conversation flow
_persona.md _general_instructions.md _actions.curls.yaml _settings.export.yaml
stages/NN_<stage>/ # strict 01..N; every file repeats the NN_ prefix
NN_enter_condition.md NN_stage_instructions.md NN_followup.md NN_actions.curls.yaml
agents/<agent>/ # same four _ files, NO stages/
knowledge_tables/*.csv # grounding data
automation_workflows/*.json # raw workflow exports — never rewrite these
_inbox/ # client intake pending consumption
_randoms/ # keep-anyway; where routed markdown lands
workspace.yml # committed, secret-free agent tooling
Commands (all npx -y loredex@latest …)
| Task | Command |
|---|---|
| New client | new client <name> --manager <m> --tags <a,b> |
| New pipeline / agent | new pipeline <client> <name> · new agent <client> <name> |
| New stage (appends NN) | new stage <client> <pipeline> <name> |
| Insert a stage | new stage <client> <pipeline> <name> --before NN (renumbers later stages via git mv) |
| Client roster + tags | clients · clients tag <client> <tag...> · untag · set-tags |
| Generate agent tooling | workspace <client> — writes gitignored .mcp.json / .claude/settings.json / AGENTS.md from workspace.yml |
| Verify tooling (CI) | workspace <client> --check (non-zero exit on drift/missing env) |
| Fleet health | doctor — schema lints, secret scan, fleet summary table |
Rules to follow
- Never create folders inside
projects/<client>/by hand — the schema is owned byloredex new, anddoctorerrors on violations (missing stage files, numbering gaps, NN prefix mismatches, agents with stages/). - Secrets never go in
workspace.yml— reference them as${ENV_VAR};workspaceexpands from the environment at generate time. Ifdoctorflags a committed secret-looking string, tell the user to rotate it (git history keeps it forever). - Definition files (
_persona.md, stage.mdfiles) are frontmatter + body: settings in frontmatter, instructions in the body. Raw exports (.yaml/.jsonunderautomation_workflows/,_settings.export.yaml) are machine truth — never rewrite. - New material from the client that has no home yet goes in
_inbox/; consuming it means moving it to its proper place (a knowledge table, a stage file) and telling the user what changed. - Research/analysis markdown you produce still follows the base
/loredexfrontmatter convention — on agent-ops dexes the router files it into the client's_randoms/.
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.
- 11d ago First seen · 71 lines · 84 tokens per session scan A bbf1063ffd19
loredex-agent-ops is a skill published in the GitHub repository ahmedtawfeeq1/loredex (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,013 once invoked, about $0.0004 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
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
handoff-protocols
Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or…
capture-task
Capture a new task — create a draft or pending Task record from a rough idea or detailed spec. Use when asked to "add a task", "log a bug", "create a task", or "add to backlog".
refine-backlog
Refine the backlog — screen drafts, remove duplicates, fill in missing details, classify, link, and move to pending.
implement-task
Pick up and work on a binder Task — investigate bugs, discuss open questions, design solutions, write tests, or implement code. Use when asked to "work on", "pick up", "implement", or "fix" a task.
daily-brief
Narrate FKF's deterministic daily control surface. Use when an owner asks to prepare the day, get a daily brief, or identify today's priorities and collection gaps.