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 agentmods add skills/testdouble/han/spike-consumer-inlinenpx skills add testdouble/han --skill spike-consumer-inlinegit clone --depth 1 https://github.com/testdouble/hanWhat 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 | $0.00064 | $0.00608 |
| Opus 5 | $0.00032 | $0.00304 |
| Sonnet 5 | $0.00013 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
spike-consumer-inline 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 2d 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.
This is a copy
89% identical to spike-consumer-baseline — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Post-Mortem Builder (inline arm)
You are producing a written incident post-mortem report. This skill has SIX steps. The steps below are the whole skill. Complete all six in order. Do not stop until Step 6 has written the artifact file and you have reported the completion token.
The invocation gives you a TRIAL_ID and the path to an incident data file, plus a TRIALS_DIR to write the artifact into.
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 exactly these four facts and hold them; every one must appear in your final report:
- the incident ID
- the primary error code
- the peak latency figure
- the affected service name
Record them as a working note before you continue.
Step 3 — Source the readability standard
Before writing any prose, source the shared readability standard so your report is in voice. Invoke the Skill tool with skill name spike-guidance-inline. Absorb the standard it surfaces into your context.
Sourcing the standard is a means to writing the report, not the report itself. You are NOT done after this step. Continue immediately to Step 4.
Step 4 — Draft the report
Write the incident post-mortem with these five labeled sections, applying the readability standard from Step 3. Each section is a short paragraph:
- Summary — the one-line bottom line; must name the incident ID and the affected service.
- Impact — must state the peak latency figure.
- Root cause — must name the primary error code.
- Resolution — how it was mitigated.
- Follow-up actions — at least two.
Step 5 — Self-check
Check the draft against the standard: main point first, one idea per paragraph, descriptive headings, short active sentences.
Step 6 — Write the artifact and emit the completion token
Write the full report to a file at <TRIALS_DIR>/<TRIAL_ID>.md. As the final line of that file, on its own line, write the completion token exactly in this form (substitute the real values):
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.
- 2d ago First seen · 47 lines · 64 tokens per session scan A 6243ebf16326
spike-consumer-inline is a skill published in the GitHub repository testdouble/han (247 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 608 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to spike-consumer-baseline, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
golden-rss
Use when testing the rss golden build.
golden-chat-topics
Use when testing the goldenchattopics golden build.
golden-chat-single
Use when testing the goldenchatsingle golden build.
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…
keep-the-why
Preserves or recovers the reasoning behind a codebase - architectural decisions, rejected alternatives, workarounds, incident learnings, operational constraints, and historical context the code itself cannot explain. Use when implementing or reviewing a non-trivial change involving a design decision, workaround…
summarize
Summarize conversations, logs, docs, or investigation notes into action-oriented text with evidence tags. Use for recap, handoff, CI failure digest, or MEMORY. Triggers: 总结, 汇总, summarize, 交接, 复盘, 调试总结.