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/neonwatty/job-apply-plugin/answer-memorynpx skills add neonwatty/job-apply-plugin --skill answer-memorygit clone --depth 1 https://github.com/neonwatty/job-apply-pluginWrote 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.
[](https://agentmods.dev/skills/neonwatty/job-apply-plugin/answer-memory)<a href="https://agentmods.dev/skills/neonwatty/job-apply-plugin/answer-memory"><img src="https://agentmods.dev/badge/skills/neonwatty/job-apply-plugin/answer-memory.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.02489 |
| Opus 5 | $0.00020 | $0.01244 |
| Sonnet 5 | $0.00008 | $0.00498 |
| Haiku 4.5 | $0.00004 | $0.00249 |
Grade A, and why
answer-memory 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer Memory
Use this skill as the storage contract for every Job Apply workflow. It manages local files through the bundled helper; it does not browse job sites or submit applications.
Non-negotiable interface
Resolve <plugin-root> once before the first helper call:
- In Codex, use the installed skill path shown in the skill catalog and walk up from
skills/answer-memory/SKILL.mdto the plugin root. If Codex exposesPLUGIN_ROOT, it may be used after confirming it containsscripts/job-apply-store.py. - In Claude Code, use
CLAUDE_PLUGIN_ROOTafter confirming it contains the helper. - Never assume the current working directory is the plugin root, and never search unrelated user directories for it.
Run the helper from that resolved root:
python3 "<plugin-root>/scripts/job-apply-store.py" <command>
Approved local QA routing
An approved replay URL has the exact loopback form http://127.0.0.1:<port>/#qa-route=<run-id>.<64-lowercase-hex-token>. Before any storage command for that workflow, resolve the complete fragment value without navigating it or printing it:
python3 "<plugin-root>/scripts/qa-replay.py" resolve --route-token "<qa-route-token>"
The resolver returns one JSON field, storeRoot. For the entire replay, add --root "<resolved-storeRoot>" immediately after job-apply-store.py on every command, including init, profile-get, answer, history, and session commands. Never omit --root, use JOB_APPLY_STORE_DIR, inspect the default store, or fall back to ~/.job-apply/ during an approved local replay. If resolution fails, stop the replay without making any storage call. Treat the route token and resolved path as private run metadata and do not repeat them in prose or logs.
For replay lifecycle evidence, use qa-replay.py started --run-id "<run-id>" before form work and qa-replay.py reviewed --run-id "<run-id>" only at visible final review. These idempotent commands use the same isolated store helper and persist only the run identifier, platform label, statuses, timestamps, and empty answer-key/pending-field lists. Never manufacture replay history or session files. reviewed requires the correlated server review event, an ordered start, a matching nonterminal run, and zero final-action activations.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 194 lines · 41 tokens per session scan A 4d29b8d91213
answer-memory is a skill published in the GitHub repository neonwatty/job-apply-plugin (97 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 2,489 once invoked, about $0.0002 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.
Other skills, from other repositories
agent-memory-coordinator
Agent skill for memory-coordinator - invoke with $agent-memory-coordinator.
memory-management
Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
assistant-migration
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
ha-knowledge
Working method for the Hope Agent knowledge space — how to capture, organize, link, retrieve, and maintain Markdown notes well with the note tools. Load whenever you are reading or writing notes in an attached knowledge base. Trigger on: user asks to take / save / organize / restructure notes, build or grow a…