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 FerroxLabs/ijfw --skill ijfw-agents-mdgit clone --depth 1 https://github.com/FerroxLabs/ijfwWrote 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/ferroxlabs/ijfw/ijfw-agents-md)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-agents-md"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-agents-md/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/ferroxlabs/ijfw/ijfw-agents-md"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 40 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00038 | $0.02701 |
| Opus 5 | $0.00019 | $0.01350 |
| Sonnet 5 | $0.00008 | $0.00540 |
| Haiku 4.5 | $0.00004 | $0.00270 |
Grade A, and why
ijfw-agents-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 4d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IJFW AGENTS.md Manager
Maintains a project's AGENTS.md per the open spec at https://agents.md/.
AGENTS.md is the canonical agent-instructions surface across every IJFW host
(Claude, Gemini, Codex, Wayland, Hermes, Cursor, Windsurf, Copilot). Each
platform-specific file (CLAUDE.md, GEMINI.md, WAYLAND.md, etc.) is a
thin adapter that points here.
When to Invoke
- User says: "agents.md", "update AGENTS.md", "regenerate agents file".
- Auto-fired by
ijfw-teamafter generating agents to.ijfw/agents/. - Auto-fired by session-start hooks to refresh memory + agents blocks.
- Auto-fired by
ijfw-workflowat brainstorm-LOCK and plan-LOCK with intent context (v1.4.4 N7).
Marker Block Taxonomy (reserved -- do not break)
The file is segmented by four IJFW-managed regions. Content outside markers is user-authored and untouched.
| Block | Purpose |
|---|---|
| MEMORY | Pointer to project memory + last handoff summary |
| ROUTING | Peer-skill routing rules (workflow, design, etc.) |
| AGENTS | Auto-generated agent definitions from .ijfw/agents/ |
| BLACKBOARD | Reserved for Pillar B (multi-CLI orchestration); empty |
| DISCIPLINE | Per-domain discipline rules (code | narrative | business | design | research) |
Each block is delimited by <!-- IJFW-<NAME>-START --> /
<!-- IJFW-<NAME>-END --> markers. Replace inside; never overwrite.
Frontmatter Contract (typed)
YAML frontmatter at top of file follows the JSON Schema at
schema/agents-md-frontmatter.json. Keys that A1 may write or hoist:
ijfw_version,ijfw_schema(required when present)type,primary_type,secondary_types,confidence(A3 writes)detected_at,signals(A3 writes)compute_trust(vm_only | subprocess),compute_net(deny | allow)
Wayland reads compute_trust + compute_net to set per-project sandbox
defaults. Env vars override only when explicitly set.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- schema/agents-md-frontmatter.json 2.6 KB
- scripts/build_blocks.py 1.8 KB runs code
- scripts/build-blocks.sh 3.0 KB runs code
- scripts/cold_scan_trigger.py 5.5 KB runs code
- scripts/cold-scan-trigger.sh 4.5 KB runs code
- scripts/hoist-frontmatter.js 5.3 KB runs code
- scripts/hoist-frontmatter.sh 2.7 KB runs code
- scripts/lock.sh 3.2 KB runs code
- scripts/merge-block-aware.sh 7.7 KB runs code
- scripts/seed-gate.sh 3.6 KB runs code
- templates/AGENTS.md.tmpl 1.1 KB
- templates/CLAUDE.md.adapter.tmpl 83 B
- templates/discipline-business.md 5.2 KB
- templates/discipline-code.md 3.5 KB
- templates/discipline-design.md 5.6 KB
- templates/discipline-narrative.md 4.7 KB
- templates/discipline-research.md 5.6 KB
- templates/GEMINI.md.adapter.tmpl 83 B
- templates/HERMES.md.adapter.tmpl 83 B
- templates/WAYLAND.md.adapter.tmpl 84 B
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.
- 4d ago First seen · 263 lines · 38 tokens per session scan A 649dedc9c500
ijfw-agents-md is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 2,701 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 2026-09-05.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
sdd-research
Trigger: SDD research, external evidence, source-backed research. Produce auditable evidence for a selected research lane.