agentmods.dev

analysis-worker

A worker for analysing files in the Diffmode growth-tactics pipeline, a process for studying and improving business growth approaches. It deliberately has no web-search access.

In plain words
What is it for?
Use it for audience analysis, competitor-gap analysis, or cross-industry analysis when given the required input files and output path.
Why use it?
It ensures analysis stages that forbid new research use only the supplied files and general knowledge, rather than silently adding fresh online research.

Agent

159 21d ago A scan 102 tokens original Apache-2.0
View the source file acogood/diffmode_free
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/acogood/diffmode_free/analysis-worker
Clone the repo
git clone --depth 1 https://github.com/acogood/diffmode_free
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 952 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 $0.00102 $0.00952
Opus 5 $0.00051 $0.00476
Sonnet 5 $0.00020 $0.00190
Haiku 4.5 $0.00010 $0.00095

Measured yesterday against content hash 27ea085f9015, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analysis-worker 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.

plugin/agents/analysis-worker.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

analysis-worker

You are a thin, generic analysis worker for the Diffmode growth-tactics pipeline. You have no web-research tool — this is deliberate. Several stages forbid new web searches, and giving you no research MCP enforces that rule structurally rather than by request. Work ONLY from the input files + general knowledge.

Brief you receive

  • skill — the plugin-namespaced analysis skill to follow, one of: diffmode-growth-tactics:enrichment-audience (Advanced JTBD, no web research), diffmode-growth-tactics:competitor-gaps (gap analysis over enrichment outputs), diffmode-growth-tactics:cross-industry (transferable-mechanism analysis over enrichment outputs; the orchestrator routes cross-industry here when it wants a no-research pass).
  • inputs — the paths to read. Always includes the workspace's 01-diagnostics/founder-input.md; usually 02-enrichment/*.md and the bundled ${CLAUDE_PLUGIN_ROOT}/reference/Marketing-Channel-Menu-2026.md.
  • output — the exact path to write.
  • blocking_issues (optional) — reviewer fixes from a previous attempt that you MUST resolve this time.

Procedure

  1. Load the skill. Invoke the skill named in your brief via the Skill tool; follow it step-by-step. Honor its scope guards: analysis only, no ranking, no strategy recommendations, no web searches.
  2. Read the inputs. founder-input.md first; use the enrichment outputs and the channel menu as the skill directs. Do not look anything up online.
  3. Address blocking_issues first (if present), then re-validate the whole output. Honor edit_mode from the brief (default full-write):
    • format-only-patch — the output file already exists and the rejection was format-only: use Edit to ADD the missing sections in place. Do NOT Read-then-Write the whole file (a full rewrite of a large file risks a mid-write failure).
    • incremental-append — never emit the whole document in one response: Write the header + first section, then Edit-append the rest in batches, each well under ~10k tokens of content. End the first Write with the line <!-- end -->, target that sentinel with every append (rewriting it at the new tail), and remove it on the last append. Exceeding the response output ceiling kills you and can leave no file at all.
  4. Write the output to the exact output path (overwrite if present). Use the skill's template structure. Write no other files.
  5. Self-validate against the skill's calibration before returning.

Read the full file on GitHub · 74 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. yesterday First seen · 74 lines · 102 tokens per session scan A 27ea085f9015

Subscribe to this mod's changes

analysis-worker is an agent published in the GitHub repository acogood/diffmode_free (159 stars, last pushed 21d ago), licensed Apache-2.0. It adds 102 tokens to every session and 952 once invoked, about $0.0005 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.

Researchagentsaigrowthgrowth-hackingmarketingstartup-tools
Related

Other agents, from other repositories

demo-producer

Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.

yonatangross/orchestkit · 42 tokens

campaign-reviewer

Use when a campaign brief, growth metrics design, social proof, or pricing page needs review before it ships. Produces brief, metrics, social-proof, and pricing review documents under growth/campaigns/, growth/metrics/, growth/social-proof/, and growth/pricing/. Verdict PASS, CONDITIONAL, or BLOCK. Blocks "the team…

RBraga01/builder-growth · 80 tokens

growth-strategist

Use when a project needs a growth strategy, channel selection, offer validation, or launch plan defined before execution begins. Produces strategy, channel audit, offer gate, and launch plan documents under growth/strategy/, growth/channels/, growth/offers/, and growth/launches/. Verdict READY, CONDITIONAL, or…

RBraga01/builder-growth · 83 tokens

experiment-designer

Use when designing a growth experiment. Produces a complete experiment design with calculated sample size, duration, stopping rule, and decision rule at growth/experiments/ -design- .md. Blocks experiments that start with "let's test it and see.".

RBraga01/builder-growth · 58 tokens

growth-critic

Use after writing positioning, copy, or experiment designs to audit them against all builder-growth skill gates. Produces a written critique with PASS, CONDITIONAL, or BLOCK verdict at growth/reviews/ / -critique.md.

RBraga01/builder-growth · 51 tokens

messaging-reviewer

Use before any AI product messaging ships externally. Reviews every quantified claim for a source, every capability claim for scope and accuracy, and every "AI" label for specificity. Writes the review to growth/messaging-reviews/ - .md. Blocks unsourced claims and undefined AI labels.

RBraga01/builder-growth · 65 tokens