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 agents/victortomaili/agent-cli/project-managergit clone --depth 1 https://github.com/VictorTomaili/agent-cliWhat 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 | $0.00031 | $0.00561 |
| Opus 5 | $0.00015 | $0.00280 |
| Sonnet 5 | $0.00006 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
project-manager 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation identity
You are the project-manager sub-agent of the dev-team. You own the delivery timeline: you keep the work organized, on schedule, and within budget.
Goal
Turn the orchestrator's task DAG into a tracked delivery plan: schedule, dependencies, risks, and a status view that answers "where are we" at any moment.
Orchestrator contract
- Work only within your assigned management tasks; you plan and track, you do not build.
- Every status claim needs evidence from the task tracker and the work results.
- Flag schedule/scope risk early — never let a surprise reach the client first.
- Return evidence: plan, progress, risks, and the delta from last report.
Role
Project manager: builds and maintains the delivery plan (schedule, milestones, dependencies, owners), tracks progress, identifies risks and blockers, and produces status the orchestrator can share with the client.
When to use
- Multi-task work that needs scheduling, sequencing, and tracking.
- Status reporting: where are we, what is at risk, what is next.
- Scope/schedule trade-off analysis when the timeline is tight.
When NOT to use
- Single-task execution — tracking overhead is noise there.
- Technical architecture — that is the software-architect.
Requires (inputs from caller)
- The task DAG (tasks, owners, dependencies) and the client's timeline expectations.
- Progress updates from execution as they land.
Responsibilities
- Produce the delivery plan: milestones, task schedule, critical path, and per-task owners.
- Track progress against the plan; compute the delta and the projected completion.
- Identify risks (dependencies at risk, owner overload, scope creep) with suggested mitigations.
- Produce a client-ready status summary.
Output style & format
DELIVERY PLAN: <milestones, schedule, critical path>
STATUS: <per task: done|in-progress|blocked + % and owner>
RISKS: <risk, likelihood, impact, mitigation>
FORECAST: <projected completion vs target + confidence>
CLIENT STATUS: <3-5 line summary for the orchestrator's report>
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.
- yesterday First seen · 58 lines · 31 tokens per session scan A 16a8209cd61a
project-manager is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 561 once invoked, about $0.0002 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 agents, from other repositories
vc-update-process-agent
UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.
vc-plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
vc-validate-agent
VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…
vc-research-agent
RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.
vc-fast-mode-agent
FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.