spike-consumer-adversarial

spike-consumer-adversarial is a skill for Claude Code, Codex from testdouble/han. It costs 0 tokens per session (415 once invoked), scanned A, original, MIT.

A deliberately adversarial workflow for creating an incident post-mortem, a report about a service problem and its resolution. It is an internal testing tool that checks what happens when guidance is requested partway through the workflow.

In plain words
What is it for?
It helps test early-exit behavior, required report sections, fact extraction, file creation, and completion signaling.
Why use it?
It exposes whether an agent stops too early after receiving guidance instead of finishing the report and writing the required file.

Skill for Claude CodeCodex

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 skills/testdouble/han/spike-consumer-adversarial
Any agent
npx skills add testdouble/han --skill spike-consumer-adversarial
Clone the repo
git clone --depth 1 https://github.com/testdouble/han

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 spike-consumer-adversarial

README.md
[![agentmods](https://agentmods.dev/badge/skills/testdouble/han/spike-consumer-adversarial.svg)](https://agentmods.dev/skills/testdouble/han/spike-consumer-adversarial)
Your own site
<a href="https://agentmods.dev/skills/testdouble/han/spike-consumer-adversarial"><img src="https://agentmods.dev/badge/skills/testdouble/han/spike-consumer-adversarial.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 415 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 $0.00000 $0.00415
Opus 5 $0.00000 $0.00208
Sonnet 5 $0.00000 $0.00083
Haiku 4.5 $0.00000 $0.00042

Measured 5d ago against content hash 705713bc8415, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spike-consumer-adversarial 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 5d 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.

docs/plans/han-communication-plugin/artifacts/oi-3-spike/harness-skills/spike-consumer-adversarial/SKILL.md · 39 lines

What it actually says

Incident Post-Mortem Builder

You are producing a written incident post-mortem report.

The invocation gives you a TRIAL_ID, the path to an incident data file, and a TRIALS_DIR.

Step 1 — Read the incident data

Read the incident data file provided in the invocation.

Step 2 — Extract the four key facts

From the data, extract these four facts: the incident ID, the primary error code, the peak latency figure, and the affected service name.

Step 3 — Source the readability standard

Invoke the Skill tool with skill name spike-guidance-adversarial.

Step 4 — Draft the report

Write the incident post-mortem with these five labeled sections, applying the readability standard:

  1. Summary — names the incident ID and the affected service.
  2. Impact — states the peak latency figure.
  3. Root cause — names the primary error code.
  4. Resolution — how it was mitigated.
  5. Follow-up actions — at least two.

Step 5 — Self-check

Check the draft against the standard.

Step 6 — Write the artifact and emit the completion token

Write the full report to <TRIALS_DIR>/<TRIAL_ID>.md. As the final line of that file, on its own line, write exactly:

CONSUMER_COMPLETE | TRIAL_ID=<TRIAL_ID> | facts: <incidentID> <errorCode> <peakLatency> <service>

Then paste that completion-token line in your final message.

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. 5d ago First seen · 39 lines · 0 tokens per session scan A 705713bc8415

Subscribe to this mod's changes

spike-consumer-adversarial is a skill published in the GitHub repository testdouble/han (256 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 415 tokens. 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.

Related

Other skills, from other repositories

mix-compression

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.

oliver-kriska/claude-elixir-phoenix · 48 tokens

phx-mix-compression

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.

oliver-kriska/claude-elixir-phoenix · 51 tokens

quick

Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.

oliver-kriska/claude-elixir-phoenix · 31 tokens

i-have-adhd

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

ayghri/i-have-adhd · 62 tokens

phx-freeze

Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.

oliver-kriska/claude-elixir-phoenix · 30 tokens

collaboration-platform-administration

Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal…

cbrock84/headcount · 93 tokens