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 Pantani/tdmcp --skill tdmcp-roadmap-campaigngit clone --depth 1 https://github.com/Pantani/tdmcpWrote 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/pantani/tdmcp/tdmcp-roadmap-campaign)<a href="https://agentmods.dev/skills/pantani/tdmcp/tdmcp-roadmap-campaign"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-roadmap-campaign/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/pantani/tdmcp/tdmcp-roadmap-campaign"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-roadmap-campaign.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 | $0.00279 | $0.02073 |
| Opus 5 | $0.00139 | $0.01037 |
| Sonnet 5 | $0.00056 | $0.00415 |
| Haiku 4.5 | $0.00028 | $0.00207 |
Grade A, and why
tdmcp-roadmap-campaign 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 9d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- tdmcp-roadmap-campaign — 100% identical, 0 lines differ
- tdmcp-roadmap-campaign — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tdmcp Roadmap-to-1.0 Campaign
Drives _workspace/campaign_roadmap_v1/ROADMAP_1.0_BACKLOG.md to completion,
gated by _workspace/campaign_roadmap_v1/ledger.json (idempotent, resumable,
merge-safe). This is orchestration only — it never writes product code
itself; it routes each ledger item to the existing specialist sub-harness and
records the outcome back into the ledger.
Why this exists (vs tdmcp-backlog-campaign)
tdmcp-backlog-campaign drives a tool-shaped backlog through one pipeline
(design→build→integrate→QA→release). The road to 1.0 is not uniform: it mixes
new tools (M4), a policy-bounded mixer slice (M5), a coverage CI gate (G2), a
bridge exec→REST sweep (G4), docs/governance (G1/G5/G6 prep), and live-validated
recipes (G3). Each needs a different specialist. This skill is the thin router
that sequences them and keeps one ledger of truth.
Confirmed campaign policy (2026-06-21)
- Release: commit + push, NO tag/bump. Everything lands in CHANGELOG
[Unreleased]. Cutting the version is a manual user step — never tag autonomously ([[no-premature-release-tag]]). - Blocked items (GPU/CUDA, live-TD, external service): build offline +
quarantine. Implement, pass the offline gates, set
liveto the rightUNVERIFIED-pending-*marker, keep going. Quarantine never blocks the campaign. - Checkpoint: after Wave 1 only, then autonomous to the end. On repeat failure: retry once → quarantine-and-continue (note it in the wave report).
Routing table (ledger route → sub-harness)
route |
Sub-harness | Agents |
|---|---|---|
docs |
tdmcp-docs-roadmap-update |
roadmap-docs-editor, docs-cookbook-sync, docs-roadmap-qa |
tools |
tdmcp-feature-lead |
tdmcp-tool-builder ×N + single-writer integration |
mixer |
tdmcp-pipeline |
mixer-scene-contract-architect, soundcraft-ui24r-adapter-architect, mixer-policy-safety-qa |
coverage |
tdmcp-test-coverage |
tdmcp-coverage-writer, tdmcp-coverage-qa |
bridge |
tdmcp-bridge-endpoint |
tdmcp-bridge-engineer (sequential — bridge slices share files) |
recipes |
tdmcp-pipeline |
td-architect, td-builder, td-qa (needs live TD) |
submission |
tdmcp-submission |
submission-architect, submission-qa |
| planning | — | tdmcp-backlog-planner (wave computation + ledger transitions) |
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.
- 9d ago First seen · 144 lines · 279 tokens per session scan A bef1dc262463
tdmcp-roadmap-campaign is a skill published in the GitHub repository Pantani/tdmcp (41 stars, last pushed 28d ago), licensed MIT. It adds 279 tokens to every session and 2,073 once invoked, about $0.0014 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 2026-09-03.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
contact-cache
Track all identified/contacted people across strategies. CSV-backed contact database with dedup by LinkedIn URL or email. Prevents duplicate outreach when running strategies on a recurring cadence.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.