AGENTS_CORE

A project-level agent instruction set built around Tiny Context, a method for keeping working context small while preserving durable project guidance and workflow rules.

In plain words
What is it for?
It is for guiding coding-agent workflows, architecture decisions, long tasks, testing, CI checks, runtime evidence, and human acceptance.
Why use it?
It helps agents stay aligned with repository evidence, required checks, recovery rules, and the level of verification appropriate to the work.

Agent for Codex

Install

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.

agentmods
npx agentmods add agents/seven128/project-tiny-context-harness/agents_core
Clone the repo
git clone --depth 1 https://github.com/Seven128/project-tiny-context-harness

Made for: Codex.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04717
Opus 5 $0.00000 $0.02358
Sonnet 5 $0.00000 $0.00943
Haiku 4.5 $0.00000 $0.00472

Measured 2d ago against content hash 5297663b544c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENTS_CORE 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 2d 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.

.codex/ty-context-managed/agents/AGENTS_CORE.md · 91 lines

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.

Minimal Context Harness Protocol

This project uses Tiny Context. The Harness maintains durable Context and workflow authority; project tests, CI, runtime evidence and human acceptance prove product quality. Its three capabilities are Minimal Context, the automatically applicable model-led default Workflow Contract for work of any complexity and the explicitly selected Single-Goal Long-Task Workflow for machine completion authority, recoverability and auditability. Complexity determines execution and verification depth; required completion authority and recoverability determine the workflow route; Long-Task-internal risk determines proof strength.

Shared Engineering Quality Obligation

Before the first implementation edit, every delivery surfaces one externally observable, repository-bound Architecture Deliberation. Depth is risk-proportional, but the checkpoint always names affected owners, the current extension point/source of truth, dependency and state/lifecycle boundaries, the selected design and material alternatives, one plausible future-change challenge, touched technical debt and its disposition, forbidden shortcuts, project-owned checks and triggered engineering-quality attributes or their concrete preservation basis. Correctness/invariants and maintainability/changeability always receive at least a preservation judgment; reliability/resource lifecycle, concurrency/consistency, performance/capacity/cost, security/privacy/safety, compatibility/migration/rollout and operability/observability/testability activate only when the change or an explicit claim makes them material. Exact product/technical predicates remain owned by Semantic Facts and exact selected UI/UX values by selected-design closure. Refresh the checkpoint when scope, ownership, selected design, quality applicability or debt disposition materially changes.

When foundational machinery, a mature protocol/security boundary, a dependency/shared abstraction or a nearby extension point makes sourcing material, include a risk-triggered Build / Reuse / Buy judgment. Record an allowed solution set, prohibited failure modes and required rationale/evidence; do not prescribe one library or abstraction. Reusing an owner, the standard library, an installed dependency, a mature compatible external library, a bounded self-implementation and intentional non-abstraction may all be valid. Enumerate every materially supported member before selection; choosing one never removes another supported member from the allowed set or turns it into a prohibited failure. Judge the task's viable set, not one rejected proposal: when at least one supported allowed choice exists, allow and select one; block only when no supported allowed choice exists, and reserve decision-required for a genuine external choice. Reject duplicate owner-held rules, extension-point bypass, unjustified heavy dependencies, plainly incomplete security-sensitive reinvention, license/platform incompatibility, forced abstraction over merely similar semantics and a second source of truth. This adds no mandatory open-source/DRY rule, quality score, stage or Gate.

Read the full file on GitHub · 91 lines

Changes

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.

  1. 2d ago First seen · 91 lines · 0 tokens per session scan A 5297663b544c

Subscribe to this mod's changes

AGENTS_CORE is an agent published in the GitHub repository Seven128/project-tiny-context-harness (3 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,717 tokens. 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.

Related

Other agents, from other repositories

acoustics-physicist

Reasons from impedance Z=p/u, Helmholtz number kL regime, and the sonar equation SL-TL-NL+DI+PG through impedance tubes (ISO 10534), anechoic and reverberation rooms, laser vibrometry, and k-Wave/COMSOL simulation while treating edge diffraction inflating absorption above one, near-field versus far-field confusion…

K-Dense-AI/scientific-agents · 104 tokens

agroecologist

Reasons from socio-ecological farm systems, functional diversity, soil-biology-mediated fertility, and yield-service trade-offs through mother-baby and mixed-model trials, N/P/C mass balances, PLFA/amplicon and pollinator surveys, and NDVI/FRAGSTATS landscape analysis, while treating edge-effect and plot-size…

K-Dense-AI/scientific-agents · 98 tokens

algorithms-researcher

Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…

K-Dense-AI/scientific-agents · 163 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens

harness-interpreter

Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.

Goldziher/basemind · 44 tokens

contextd-reviewer

Review output against contracts/patterns/domain rules referenced by .contextd/context/current-task.json. Markdown is render-only; JSON artifact is canonical.

philngt/contextd · 34 tokens