Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Redtropig/harness-anchor/plugin install harness-anchorWrote 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/redtropig/harness-anchor/project-indexing)<a href="https://agentmods.dev/skills/redtropig/harness-anchor/project-indexing"><img src="https://agentmods.dev/badge/skills/redtropig/harness-anchor/project-indexing/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/redtropig/harness-anchor/project-indexing"><img src="https://agentmods.dev/badge/skills/redtropig/harness-anchor/project-indexing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00034 | $0.01003 |
| Opus 5 | $0.00017 | $0.00502 |
| Sonnet 5 | $0.00007 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
project-indexing 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 12d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Indexing
PROJECT-TOC.md is the project's machine-friendly index — one line per file, ≤80 chars summary. Reading it is dramatically cheaper than Glob-ing the whole tree.
When to use
- "Where is X defined?"
- "Find the file that handles Y"
- Before any
Glob '**/*.ext'against more than a small directory - When starting work in an unfamiliar codebase
Reading flow
-
Check
PROJECT-TOC.mdexists. If missing, the project is un-indexed. Suggest/index-projectand fall back to Glob for the current question. -
Check freshness. The TOC header contains:
<!-- generated-at-commit: <SHA> -->Stale if either (both counts exclude
PROJECT-TOC.mditself, so committing a regenerated TOC does not re-stale it):git diff --name-only <SHA> HEADreturns filesgit status --porcelainshows working-tree changes (untracked files count — the TOC doesn't cover them)
Note: the SessionStart hook already computes
toc_stale: true/falseand injects it. If stale, prefer/index-projectbefore deep navigation; for one-off questions, fall back to Glob. -
Forest before trees. Read the
## Directory mapfirst (one line per directory, with file + subdir counts) to find the right subtree, then grep/scan the## Filesentries under that path. On a large repo the SessionStart hook injects only the directory map (or just its top levels), so the per-file leaves are read on demand. -
Open the file. Only after locating via TOC.
When NOT to rely on TOC
- TOC was just regenerated but agent hasn't seen it (mtime ≠ session start)
- File you're looking for is new (not yet in git)
- Question requires content search, not name search (use Grep then)
Rebuilding
When you make significant structural changes (new directories, renames, large refactors):
node ${CLAUDE_PLUGIN_ROOT}/scripts/index-builder.mjs --target .
Or simply tell the user to run /index-project. Don't try to maintain the TOC by hand-editing — it's auto-generated.
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.
- 12d ago First seen · 96 lines · 34 tokens per session scan A 50cadd74f631
project-indexing is a skill published in the GitHub repository Redtropig/harness-anchor (13 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,003 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 2026-08-30.
Other skills, from other repositories
remember
Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…
context-degradation
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
context-compression
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.
context-fundamentals
This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other…
context-optimization
This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.
filesystem-context
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup policies for context stored outside the prompt.