Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-appnpx agentmods add skills/saeedkolivand/ai-job-hunter-app/lessonsWrote 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/saeedkolivand/ai-job-hunter-app/lessons)<a href="https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/lessons"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/lessons/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/lessons"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/lessons.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.00465 |
| Opus 5 | $0.00023 | $0.00233 |
| Sonnet 5 | $0.00009 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
lessons 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 7d 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.
What it actually says
Lessons — distilled experiential memory
Store: .claude/memory/lessons.jsonl (local, capped 200, archived on overflow). Only project-steward writes.
Query (any agent, on-demand)
node .claude/hooks/lessons.mjs query --domain export
node .claude/hooks/lessons.mjs query --category Performance
node .claude/hooks/lessons.mjs query --text "pagination"
Returns only matching ≤5-line lessons — never bulk-loaded. The review-gate auto-queries by touched domain/globs and folds matches into its prompt.
Propose (any agent)
Surface as: LESSON · <category> · Context: … · Decision: … · Outcome: … (≤5 lines). project-steward dedupes & persists.
Tag the memory type in --tags — a free-form convention (not enforced by lessons.mjs), following the 2026 agent-memory taxonomy: episodic (a specific past event/fix), semantic (a durable fact/convention), or procedural (a workflow / review convention / test command / tool-use habit). Procedural lessons are the highest-leverage — capture "how we do X here."
Categories (exactly one)
Architecture decision · Failed approach · Proven approach · Performance · Security · ATS · Scraping · AI-provider · Export · Testing discovery.
Rules
- Distilled lessons only — never raw conversations / task-histories / review-outputs.
Context · Decision · Outcome, ≤5 lines.- Dedupe on add; cap 200 active; archive the rest.
- An Architecture-decision lesson that graduates to an ADR (
docs/knowledge/decision-records/) is removed from the log — the ADR becomes its single source. - Context priority stays: graphify → source → docs/knowledge → lessons.
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.
- 7d ago First seen · 37 lines · 45 tokens per session scan A 86fe4d9c4750
lessons is a skill published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 465 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 2026-09-03.
Other skills, from other repositories
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
role-skill-boundary-audit
Audit where governance instructions belong (Role.md, skill, global policy, workflow docs, memory, or an agent-boundary change); enforce minimal verbosity in roles and skills. Diagnostic by default.
memory-system
Persistent cross-session memory management. Enables agents to remember user preferences, project conventions, and past decisions across different sessions using a structured MEMORY.md index and topic files.
context-compression
Manage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.
resume-builder
Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON…
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…