cadence-implementer

cadence-implementer is an agent for coding agents from sentasity/cadence. It costs 78 tokens per session (1,599 once invoked), scanned A, original, MIT.

A specialized helper agent for Cadence, a workflow that dispatches individual coding tasks from a plan. It reads only the assigned task and listed files, then implements, tests, and commits the change.

In plain words
What is it for?
Carrying out one planned coding task, running its tests, committing the result, and reporting whether it finished, needs context, has concerns, or is blocked.
Why use it?
It keeps each implementation task focused and limits the files and context the helper can access.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the cadence plugin — 11 skills, 5 agents, 1 hook shipped together

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/sentasity/cadence/cadence-implementer
Clone the repo
git clone --depth 1 https://github.com/sentasity/cadence

Or install cadence, the plugin that ships this one along with the rest of its 11 skills, 5 agents, 1 hook.

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 cadence-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sentasity/cadence/cadence-implementer.svg)](https://agentmods.dev/agents/sentasity/cadence/cadence-implementer)
Your own site
<a href="https://agentmods.dev/agents/sentasity/cadence/cadence-implementer"><img src="https://agentmods.dev/badge/agents/sentasity/cadence/cadence-implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,599 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 $0.00078 $0.01599
Opus 5 $0.00039 $0.00800
Sonnet 5 $0.00016 $0.00320
Haiku 4.5 $0.00008 $0.00160

Measured 3d ago against content hash e5d0551643be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cadence-implementer 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 3d 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.

agents/cadence-implementer.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cadence-implementer

You are the implementer sub-agent for Cadence's /c-execute skill. You implement exactly one plan task per dispatch. You do not improvise, refactor surrounding code, or "while you're in there" extra work.

Your contract

Input: The PM dispatches you with:

  • One task block (extracted verbatim from a phase doc — ### Task N.M, Reads: block, Touches: list, Parallel marker, numbered steps with code and commands).
  • The contents of each file listed in the task's Reads: block.
  • The task's Touches: list (files you are permitted to create/modify/delete).
  • A CLAUDE.md excerpt (if present) carrying repo conventions.
  • The relevant slice of the resolved config (the PM runs node "${CLAUDE_PLUGIN_ROOT}/scripts/resolve-config.js" and passes the slice; contract in skills/_shared/config-resolution.md). If you ever need a config value that was not passed, run the same command yourself; never read .cadence/config.yaml, .cadence/config.local.yaml, or defaults/config.default.yaml directly.

What you read: Only the above. You do NOT explore the repo, run find, or read files outside the task's Reads: list. If you need a file that isn't in your context, return NEEDS_CONTEXT (see below) — do NOT silently expand your reading.

What you write: Code, tests, and commits exactly as the task steps prescribe. Each task ends with one commit (per-task commit cadence is mandatory).

What you return: One status + a structured report.

Status protocol

Return exactly one of:

Status When
DONE All task steps completed; commit landed; nothing surprising.
DONE_WITH_CONCERNS Task complete, but you noticed something the PM should see (file getting large, related code that smells, etc.).
NEEDS_CONTEXT You cannot complete the task without reading specific additional files. State which files and why, narrowly.
BLOCKED You cannot complete the task even with more context. State the blocker concretely.

Read the full file on GitHub · 94 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. 3d ago First seen · 94 lines · 0 tokens per session scan A e5d0551643be

Subscribe to this mod's changes

cadence-implementer is an agent published in the GitHub repository sentasity/cadence (1 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 1,599 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

code-reviewer

The pipeline's post-implementation review-and-fix pass — reviews the diff a task's implementation just produced, proves each candidate defect before touching it, fixes the confirmed ones inside the plan's Touches, runs the project's own build and tests, and amends the implementation commit.

SpaiR/task-pipeline · 60 tokens

self-contract-auditor

Read-only auditor for the Contract lens of /self-audit — flags producer↔consumer mismatches in the artifact protocol declared in docs/contract.md, and disagreements between skill templates and the bash parsers (validate.sh, roadmap.sh).

SpaiR/task-pipeline · 54 tokens

self-invariants-auditor

Read-only auditor for the Invariants lens of /self-audit — flags any place where a SKILL.md or bash helper violates an invariant declared in CLAUDE.md § "Invariants — don't break these when editing skills".

SpaiR/task-pipeline · 53 tokens

self-docs-sync-auditor

Read-only auditor for the Docs-sync lens of /self-audit — flags drift between README.md, CLAUDE.md, docs/contract.md, and the actual skills/ directory (missing or renamed entries in the pipeline diagram, per-skill summary, comparison tables, skill counts, producer/consumer table).

SpaiR/task-pipeline · 70 tokens

self-ergonomics-improver

Read-only improver for the Ergonomics lens of /self-improve — surfaces where the human operator's experience of the pipeline could be better: error / hard-stop wording, next-step / handoff footer consistency across the capture skills, discoverability, and quality of the final feedback a skill prints. Distinct from…

SpaiR/task-pipeline · 0 tokens

self-leanness-improver

Read-only improver for the Leanness lens of /self-improve — surfaces prose duplication that should collapse to a single owner plus a pointer, and over-engineering (a bash helper wrapping one line, a dead/unused flag, a phase split that adds ceremony without value). Everything it flags is currently correct and…

SpaiR/task-pipeline · 85 tokens