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 skills add davidYichengWei/Agency --skill reflectgit clone --depth 1 https://github.com/davidYichengWei/AgencyWrote 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/davidyichengwei/agency/reflect)<a href="https://agentmods.dev/skills/davidyichengwei/agency/reflect"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/reflect.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 5.1 | $0.00077 | $0.00874 |
| Opus 5 | $0.00039 | $0.00437 |
| Sonnet 5 | $0.00015 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00087 |
Grade A, and why
reflect 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement
Why this exists
The harness's goal is a digital employee who compounds knowledge over time — each task should leave the harness slightly better equipped for the next one. Reflections are the capture step; promoting them into rules, skills, and memory is what closes the loop and reduces the amount of human intervention a similar future task needs.
Your job here: notice what would materially change how an agent approaches a similar future task, write it down, and suggest where it belongs.
What to capture
Anything specific to this project, this codebase, this user, or this environment that would measurably reduce exploration, retries, mistakes, or missed details on a similar future task.
Use your judgment about what qualifies — don't work off a fixed checklist. If you can state the lesson in one line that would materially change future behavior, and a generic senior engineer arriving fresh to this project would NOT already know it, it's worth capturing.
Skip general software engineering advice. The model already has that.
Where to write
Append to .agent/<task-name>/reflection.md.
Format
Each entry:
### [YYYY-MM-DD] <one-line lesson, phrased as guidance>
**Context**: <what happened or why this matters — 1-2 lines>
**Suggested promotion**: <rule | skill | memory> — <rationale; name the target file, or "new file: <name>" if none fits>
The three promotion targets:
- rule — always-on behavioral guardrail (
claude/rules/*.md). Use for behaviors that should apply to every task. - skill — on-demand knowledge or procedure (
claude/skills/<name>/SKILL.md). Use for domain knowledge or workflow recipes loaded when needed. - memory — persistent per-project fact or user preference (
~/.claude/projects/<repo>/memory/*.md). Use for facts about this project or this user.
Promotion itself is human-approved — you suggest, the user confirms and moves the content into the target file. Never create rules or skills autonomously.
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 · 76 lines · 77 tokens per session scan A 638e5f6bb7b1
reflect is a skill published in the GitHub repository davidYichengWei/Agency (5 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 874 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.