tdmcp-backlog-campaign

tdmcp-backlog-campaign is a skill for Claude Code, Codex from Pantani/tdmcp. It costs 185 tokens per session (3,403 once invoked), scanned A, original, MIT.

A release workflow for taking an entire tdmcp feature backlog through several resumable waves of implementation.

In plain words
What is it for?
Use it when implementing a whole discovery file or backlog; a single feature belongs in a smaller feature-building workflow.
Why use it?
It keeps many features organized with shared sequencing, progress tracking, recovery, and release checkpoints.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

Good fit Use it when implementing a whole discovery file or backlog; a single feature belongs in a smaller feature-building workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pantani/tdmcp/tdmcp-backlog-campaign
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.

Any agent
npx skills add Pantani/tdmcp --skill tdmcp-backlog-campaign
Clone the repo
git clone --depth 1 https://github.com/Pantani/tdmcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tdmcp-backlog-campaign

README.md
[![agentmods](https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-backlog-campaign/github.svg)](https://agentmods.dev/skills/pantani/tdmcp/tdmcp-backlog-campaign)
Your own site
<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.

agentmods 80×15 button for tdmcp-backlog-campaign

Your own site · 80×15
<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>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00185 $0.03403
Opus 5 $0.00093 $0.01702
Sonnet 5 $0.00037 $0.00681
Haiku 4.5 $0.00018 $0.00340

Measured 11d ago against content hash 36fd586cd597, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.agents/skills/tdmcp-backlog-campaign/SKILL.md · 207 lines

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

  1. The ledger (_workspace/campaign_<id>/ledger.json, in the main repo checkout — resolve with dirname "$(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.mjs beside 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
    
  2. 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.

Read the full file on GitHub · 207 lines

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. 11d ago First seen · 207 lines · 185 tokens per session scan A 36fd586cd597

Subscribe to this mod's changes

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.