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 instructions/pavelpilyak/devrecall/claude-mdgit clone --depth 1 https://github.com/pavelpilyak/devrecallWrote 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/instructions/pavelpilyak/devrecall/claude-md)<a href="https://agentmods.dev/instructions/pavelpilyak/devrecall/claude-md"><img src="https://agentmods.dev/badge/instructions/pavelpilyak/devrecall/claude-md.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 | $0.01350 | $0.01350 |
| Opus 5 | $0.00675 | $0.00675 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
devrecall CLAUDE.md 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 6d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevRecall
On-device developer activity aggregator — generates AI-powered standups, perf reviews, and work memory from Git, Slack, Calendar, Jira, and Linear. All data stays local.
Tech Stack
- Language: Go
- Database: SQLite (WAL mode, FTS5 for search)
- CLI framework: cobra
- LLM: Ollama (local) + BYOK (OpenAI/Anthropic)
- Embeddings: all-MiniLM-L6-v2 via ONNX (bundled)
Project Structure
cmd/devrecall/ CLI entrypoint
internal/
agent/ Chat agent loop + read-only tool catalogue (agent/tools/)
api/ Local HTTP API (localhost:3725) for desktop app + integrations
auth/ OAuth flows + token storage (keychain/file-based)
chat/ Interactive chat REPL with conversation memory
collector/ Source integrations
collector.go Collector interface
git/ Git log parsing
github/ gitlab/ bitbucket/ PRs, reviews, issues, comments
slack/ Slack API
calendar/ Google Calendar API
jira/ confluence/ Atlassian (shared token)
linear/ Linear GraphQL API
notion/ Notion pages (internal integration token)
claudecode/ Claude Code sessions from local ~/.claude transcripts
ticketlink/ Ticket-key extraction from commit/PR text
ratelimit/ Shared HTTP rate limiting
config/ App configuration (~/.devrecall/config.json)
daemon/ Background sync daemon (launchd)
embedding/ Vector embeddings (ONNX bundled, Ollama, OpenAI)
enrich/ LLM enrichment of activities (tags, summaries)
identity/ Cross-source identity resolution (email-based)
llm/ LLM provider abstraction (Ollama, OpenAI, Anthropic)
mcp/ MCP server (stdio) exposing the agent tool catalogue
pipeline/ Post-sync passes: work-item linking, enrichment, embedding
privacy/ Redaction / privacy filters
storage/ SQLite layer — activities, FTS5, sqlite-vec, hybrid retrieval
(hybrid.go fuses FTS5 + vector via Reciprocal Rank Fusion)
summarizer/ LLM-powered summary generation (standup, weekly, brag, perf review)
update/ Self-update + release checks (GitHub) and kill-switch manifest
workitem/ Work-item grouping across sources (ticket-keyed)
pkg/models/ Shared domain types (Activity, Identity, Summary)
relay/ Cloudflare Worker — OAuth callback relay (TypeScript)
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.
- 6d ago First seen · 91 lines · 1,350 tokens per session scan A 9ac3c7c6e70f
devrecall CLAUDE.md is an instructions file published in the GitHub repository pavelpilyak/devrecall (4 stars, last pushed 7d ago), licensed MIT. It adds 1,350 tokens to every session, about $0.0068 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.