Engram is a local or cloud-backed memory system for AI coding agents, provided as a single Go binary with SQLite full-text search and interfaces including a command line, HTTP API, MCP server, and terminal UI. It helps compatible coding agents retain project decisions, bugs, conventions, and other useful context across sessions. The catalogue add-ons configure and operate Engram’s memory workflows.
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 Gentleman-Programming/engram --skill testing-coveragegit clone --depth 1 https://github.com/Gentleman-Programming/engramWrote 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/gentleman-programming/engram/testing-coverage)<a href="https://agentmods.dev/skills/gentleman-programming/engram/testing-coverage"><img src="https://agentmods.dev/badge/skills/gentleman-programming/engram/testing-coverage/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/gentleman-programming/engram/testing-coverage"><img src="https://agentmods.dev/badge/skills/gentleman-programming/engram/testing-coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00386 |
| Opus 5.5 | $0.00010 | $0.00154 |
| Sonnet 5.5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
engram-testing-coverage 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 21d 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
When to Use
Use this skill when:
- Adding new behavior
- Fixing a bug
- Refactoring logic with branch complexity
TDD Loop
- Write a failing test for the target behavior.
- Implement the smallest code to pass.
- Refactor while keeping tests green.
- Add edge/error-path tests before closing.
Coverage Rules
- Cover happy path + error paths + edge cases.
- Prefer deterministic tests over flaky integration paths.
- Add seams only when branches are impossible to trigger naturally.
- Keep runtime behavior unchanged when adding seams.
Verification Ownership
Verification is evidence about the candidate; CI is the automated execution venue, not a substitute for local focused evidence.
- For behavior changes, run a focused regression test and tests for the affected package(s) locally before proposing the change. Report the commands and outcomes.
- Use targeted coverage when useful to find missed behavior or branches. Do not require a numeric coverage target or total module coverage for every PR.
- After the candidate is pushed to a PR, GitHub CI owns the full unit suite (
go test ./...), E2E suite (go test -tags e2e ./internal/server/...), lint, and applicable platform checks. Do not report CI evidence until those checks actually run. - When there is no PR or the candidate is unpushed, or when risk justifies more verification, run the additional applicable checks locally. Report checks that could not run as missing evidence rather than claiming CI covered them. Avoid duplicating the broad suite locally by default when PR CI will run it.
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.
- 21d ago Changed · -2 lines 20df00f0a88e
- 1mo ago First seen · 49 lines · 25 tokens per session scan A 94b7e626c8e3
engram-testing-coverage is a skill published in the GitHub repository Gentleman-Programming/engram (7,360 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 386 once invoked, about $0.0001 per session on Opus 5.5. 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
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.