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-backlog-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-backlog-campaign)<a href="https://agentmods.dev/skills/pantani/tdmcp/tdmcp-backlog-campaign"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-backlog-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-backlog-campaign"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-backlog-campaign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00185 | $0.03403 |
| Opus 5 | $0.00093 | $0.01702 |
| Sonnet 5 | $0.00037 | $0.00681 |
| Haiku 4.5 | $0.00018 | $0.00340 |
Grade A, and why
tdmcp-backlog-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 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- tdmcp-backlog-campaign — 100% identical, 0 lines differ
- tdmcp-backlog-campaign — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tdmcp-backlog-campaign — whole-backlog delivery
A single feature-build wave is already handled well by tdmcp-pipeline (the
five specialists) and tdmcp-feature-lead (parallel builders + single-writer
integrate). This skill is the layer they do not provide: driving an entire backlog
of dozens of features to completion across multiple themed releases, resumably.
It is a thin, ledger-driven loop over the existing pipeline — it adds idempotency,
resilience, shared-schema sequencing, and a checkpoint/release policy; it does not
re-implement building.
When NOT to use this: one feature, or one small ad-hoc batch →
tdmcp-pipeline. A whole survey/backlog file, "all the features", or "continue the campaign" → here.
The two things this skill owns
- The ledger (
_workspace/campaign_<id>/ledger.json, in the main repo checkout — resolve withdirname "$(git rev-parse --path-format=absolute --git-common-dir)", never the worktree, so state survives worktree cleanup and is shared across sessions). One row per feature;build-ledger.mjsbeside it regenerates the static plan merge-safely (preserves live state). This is the idempotency + resilience substrate. Status vocabulary:pending → designing → building → integrating → qa → shipped side: blocked-dep | blocked-td | quarantined | merged | tracked-elsewhere - The wave/release loop — pick the next ready wave (via
tdmcp-backlog-planner), run it through the pipeline foundations-first, release it under policy, fold the results back into the ledger, then checkpoint or continue.
Execution policy — read it from ledger.policy, do not assume
The ledger carries the policy the user chose; honor it literally. For the current
campaign (beyond_20260530):
| Policy | Value | Meaning |
|---|---|---|
scope |
staged-by-priority |
Run waves in order; pause after checkpoint_after_wave for a go/no-go before continuing. |
checkpoint_after_wave |
1 |
After wave 1 (P0 + Top-12) ships, stop and report; wait for the user to say continue. |
release |
commit-and-push-NO-tag |
The releaser writes CHANGELOG + bumps version + commits + pushes the branch, but must NOT git tag (the repo's tags diverged; tagging is held). |
td_required_before_build_waves |
true |
A wave touching needs_td features only runs when get_td_info reports connected. If offline, hold those features (blocked-td) and say so; never fake a live pass. |
builder_retry |
1 |
One retry per failing builder/feature. |
on_repeat_fail |
quarantine-and-continue |
After the retry, mark quarantined, record the gap, and keep the wave moving — one stuck tool never blocks the rest. |
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 · 207 lines · 185 tokens per session scan A 36fd586cd597
tdmcp-backlog-campaign is a skill published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 26d ago), licensed MIT. It adds 185 tokens to every session and 3,403 once invoked, about $0.0009 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.
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.