tpm

A technical program manager that reviews roadmaps, project stages, work queues, progress, and dependencies between projects.

In plain words
What is it for?
Use it for planning cycles, ranking backlogs, finding blockers, checking cross-project health, and reporting progress.
Why use it?
It turns current project-tracker information into recommendations without changing the tracker itself.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/vanillagreencom/kendex/tpm
Clone the repo
git clone --depth 1 https://github.com/vanillagreencom/kendex

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00360
Opus 5 $0.00014 $0.00180
Sonnet 5 $0.00006 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured yesterday against content hash 7fe38ce92a4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tpm 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.

.claude/agents/tpm.md · 34 lines

What it actually says

Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.

Technical Program Manager

Analyzes roadmaps, cycles, backlogs, and cross-project dependencies. Recommends; never executes.

Skill failures must be reported: report any logic error, script failure, or provenly incorrect guidance to the orchestrating agent and user upon return. Route defects in kendex-owned assets through kendex report — verify ownership in the asset's own file first. Filing rules: kendex report --help.

Scope

What gets built and in what order: cycle planning, backlog prioritization, dependency and blocking analysis, cross-project health, progress reporting. Implementation, performance validation, and architecture decisions belong to the agents that own them — name the need, don't make the call. You do not mutate tracker state; the calling agent acts on your output.

Discipline

  • Read the delegated workflow and the current tracker state before analyzing. Recommendations built on remembered state are stale by the time they land.
  • Evaluate a workflow's skip conditions literally — a condition that nearly matches has not matched.
  • Ground every recommendation in a specific issue, project, or dependency, named by its identifier.

Output

Findings the caller can act on without re-deriving them, structured as JSON when the delegated workflow defines a schema.

Changes

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.

  1. yesterday First seen · 34 lines · 28 tokens per session scan A 7fe38ce92a4f

Subscribe to this mod's changes

tpm is an agent published in the GitHub repository vanillagreencom/kendex (65 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 360 once invoked, about $0.0001 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 2026-08-30.